[{"data":1,"prerenderedAt":990},["ShallowReactive",2],{"blog-en-don-t-let-your-data-strategy-slow-your-business-down":3,"related-en-don-t-let-your-data-strategy-slow-your-business-down":185},{"id":4,"title":5,"author":6,"body":7,"category":6,"description":13,"extension":168,"image":169,"isToc":170,"langAlt":6,"meta":171,"metaDescription":6,"navigation":172,"path":173,"published":172,"publishedAt":174,"readingTimeMinutes":175,"readingTimeText":176,"relatedArticles":177,"seo":181,"stem":182,"teaser":183,"updatedAtCustom":6,"__hash__":184},"blog_en\u002Fen\u002Fblog\u002Fdon-t-let-your-data-strategy-slow-your-business-down.md","Don’t let your data strategy slow your business down",null,{"type":8,"value":9,"toc":156},"minimark",[10,14,22,27,30,37,40,44,47,50,53,59,65,74,79,82,86,89,93,96,100,108,113,118,124,128,131,137,140,149],[11,12,13],"p",{},"Incorrect decisions can have a damaging impact. Companies gather their resources to combine different data sources, new data streams with existing data, and apply analytics to find connections for better and quicker decisions.",[11,15,16,17,21],{},"Surveys conducted on the advancement of data maturity show that ",[18,19,20],"strong",{},"majority of companies haven’t reached their wished goals"," despite the excessive investments and numerous attempts. What most companies don’t accept is the amount of effort required to become data-driven and the time progress as well.",[23,24,26],"h2",{"id":25},"common-problems","Common problems",[11,28,29],{},"The most frequent problems businesses face are process efficiency and insufficient improvement of customers’ experience. What can be seen as a first and fastest action to skip the process and suddenly become a data transformation is acquiring the newest and the most expensive technology, without understanding its real purpose, internal process coordination, and company culture. Employees across departments commonly struggle to gain practical insights from available information that are accurate and in time and be able to base their decision on facts, not just estimations.",[11,31,32,33,36],{},"To be able to extract valuable insights from data, ",[18,34,35],{},"smart investment"," in the right technology is essential while keeping in mind the data lifecycle. Moving forward, or upward requires the knowledge of the current situation.",[11,38,39],{},"Many companies wonder, how to up their game and grow with data. There are various options on how to ensure faster business growth via the right and individually adjusted data strategy. However, the higher and more advanced data strategy, or better known as Data Maturity, needs to be aligned with the business maturity.",[23,41,43],{"id":42},"data-maturity","Data Maturity",[11,45,46],{},"Data Maturity measures how advance is the data analysis and data utilization of the organization. As the companies increase the use of their data, they develop more complex data analytics and processing, the higher stage they achieve.",[11,48,49],{},"Maturity should be seen as a long-term goal and is achieved continually, involving many actions. It is iterative and progressive; therefore, companies evolve in smaller projects, which can be broken down into smaller steps, making the progress comprehensible.",[11,51,52],{},"Over the years we have cooperated with companies from different stages of the Data Maturity Model, small companies that are starting to combine their data into one stream, while others have integrated advanced machine learning. From the projects we helped to grow, we have acknowledged four stages of data maturity.",[11,54,55,56],{},"Companies that achieved the top level, leverage their increased agility, better partner and supplier cooperations via integration, utilizing data, and predictive analytics. They ",[18,57,58],{},"monetize the data and benefit from significant competitive advantage.",[11,60,61,62],{},"Just naming or defining the phases may not illustrate the true height of the steps, companies have to climb to score the next stage. ",[18,63,64],{},"The gap is bigger than it seems.",[11,66,67],{},[18,68,69],{},[70,71],"img",{"alt":72,"src":73},"","\u002Fupload\u002Fdata-maturity-model.webp",[75,76,78],"h3",{"id":77},"_1-data-novice","1. Data Novice",[11,80,81],{},"In the first stage, the company initializes the data journey with manual non-standardized reporting in different systems, different data sources. The firm recognizes the need for collecting data without building a data structure or systematic analysis. The reports are often irregular, and the business does not rely on its data. Usually, SME and startups are in this phase.",[75,83,85],{"id":84},"_2-data-standardized","2. Data Standardized",[11,87,88],{},"Data storage is incomplete, and the company uses multiple databases, and the biggest question is data quality. The company is ready to start data initiative and is looking for know-how on how to manipulate or use the data. What can be seen here is that IT hits a wall of capacity and capability to advance the data strategy.",[75,90,92],{"id":91},"_3-data-advanced","3. Data Advanced",[11,94,95],{},"Critical decisions are based on data. Data is being broken down throughout the entire organization and it is used as a competitive differentiator. Executive engagement is needed for reaching a higher level. Optimization of data storage and platforms is required to keep up with the demand.",[75,97,99],{"id":98},"_4-data-driven","4. Data-Driven",[11,101,102,103,107],{},"A phase characterized as ",[104,105,106],"em",{},"no data - no decision",". Technologies and business reached tight cooperation and are fully integrated. The company has been able to identify the processes for data analytics implementation and it became part of every company process, reaching prescriptive analytics. The speed of interactions in development increases. The data infrastructure is secure, yet it needs to be able to recognize the attacks and reacts to all the changes in real-time.",[109,110,112],"h4",{"id":111},"comparison-of-each-stage-by-characteristics-and-focus","Comparison of each stage by characteristics and focus",[11,114,115],{},[70,116],{"alt":72,"src":117},"\u002Fupload\u002Fmaturiy-compared.webp",[11,119,120,121],{},"For a transformation to becoming a data-driven organization, true differentiation lays in a strategic decision of leadership and treating the company’s data as a strategic asset. From the data collection throughout the whole data flow and architecture, up to its visualization, ",[18,122,123],{},"exploring new opportunities of modern and adequate technology separates the market leaders from the followers.",[23,125,127],{"id":126},"conclusion","Conclusion",[11,129,130],{},"Rising to a higher stage of data maturity takes a greater amount of resources, especially time and investment in technology and talents. With the growing amount of data produced each day, the returns of the investment come sooner in the form of more loyal customers, higher conversions, cost reduction, and much more.",[132,133,136],"action",{"link":134,"button":135},"\u002Fen\u002Fget-in-touch\u002F","Just ask us!","\nDo you want to know, how far have you already come and how to move up? We can help you move up the ladder and improve your data strategy.\n",[11,138,139],{},"Get to know our solutions:",[11,141,142],{},[143,144,148],"a",{"href":145,"rel":146},"https:\u002F\u002Fcrossmasters.com\u002Fen\u002Fproducts\u002Fmeasurement-hub\u002F",[147],"nofollow","Measurement Hub",[11,150,151],{},[143,152,155],{"href":153,"rel":154},"https:\u002F\u002Fcrossmasters.com\u002Fen\u002Fwhat-we-do\u002Fmadtech\u002F",[147],"MAdTech architecture audit",{"title":72,"searchDepth":157,"depth":157,"links":158},2,[159,160,167],{"id":25,"depth":157,"text":26},{"id":42,"depth":157,"text":43,"children":161},[162,164,165,166],{"id":77,"depth":163,"text":78},3,{"id":84,"depth":163,"text":85},{"id":91,"depth":163,"text":92},{"id":98,"depth":163,"text":99},{"id":126,"depth":157,"text":127},"md","\u002Fupload\u002Fdata-strategy-article-cover.webp",false,{},true,"\u002Fen\u002Fblog\u002Fdon-t-let-your-data-strategy-slow-your-business-down","2020-06-25T12:00:00.000+00:00",4.555,"5 min read",[178,179,180],"content\u002Fen\u002Fblog\u002Fincrease-conversions-with-category-page-product-ranking.md","content\u002Fen\u002Fblog\u002Fpractical-use-of-cognitive-computing.md","content\u002Fen\u002Fblog\u002Fquick-trip-beyond-data-quality.md",{"title":5,"description":13},"en\u002Fblog\u002Fdon-t-let-your-data-strategy-slow-your-business-down","Data can answer not only business questions and delivers value. Dependable alignment between technology and business accelerates the path from data to decision. ","P1RPwQLJY0uFHr3e_e9MRYd9p-I0y_2uJMOFWtaPKcI",[186,424,805],{"id":187,"title":188,"author":6,"body":189,"category":410,"description":193,"extension":168,"image":411,"isToc":170,"langAlt":6,"meta":412,"metaDescription":6,"navigation":172,"path":413,"published":172,"publishedAt":414,"readingTimeMinutes":415,"readingTimeText":416,"relatedArticles":417,"seo":420,"stem":421,"teaser":422,"updatedAtCustom":6,"__hash__":423},"blog_en\u002Fen\u002Fblog\u002Fincrease-conversions-with-category-page-product-ranking.md","Increase conversions with category page product ranking",{"type":8,"value":190,"toc":397},[191,194,201,205,208,212,215,219,222,226,229,233,236,241,245,248,252,255,259,262,266,269,273,276,280,283,287,291,294,298,301,305,308,359,363,366,383,386,393],[11,192,193],{},"Traditionally, e-commerce retailers and marketers pay most of their attention to developing product pages and checkout pages, because that is where the sales happen. However, we need to look at the previous steps, before the checkout. Customers use category pages to understand the offers of the e-shop, in other words, category pages become the attraction locations.",[11,195,196,197,200],{},"When a customer comes to an e-shop and looks for a product, category pages drive the majority of the site product discovery ranging between 50 - 70%, compared with other options, search results and recommendation sites bring around 10% each. This may seem like a lot and that there is not much to be improved. Nevertheless, t",[18,198,199],{},"he issue is in the progress from the category page."," When the category page is not compelling enough, customers are unlikely to reach the individual product page. Less than half of that traffic really proceeds to the product page. Customers probably did not find what they were looking for, the products were not relevant or outside their price range. By optimizing category pages, you can double the product discovery and increase the profit. Additionally, it builds a website structure, improves SEO, and subsequent remarketing advertising.",[23,202,204],{"id":203},"improving-category-pages","Improving category pages",[11,206,207],{},"Driving targeted traffic to category pages has been a topic of many marketers’ discussion. Commonly they have already adopted some improvements. The “science” behind the sales-driving category pages lies in displaying the optimal combination of selected products, counting on the limited number of the showed pieces. Here are just two examples, how usually e-shops try to tackle category pages:",[109,209,211],{"id":210},"manual-optimization","Manual optimization",[11,213,214],{},"The cooperation with many e-commerce businesses helped us understand that many e-shops are trying to optimize the category pages, however, they do it manually and rely on their own intuition rather than customer’s behavior. Manual arrangements can take days resulting in wasted resources; energy, time, and finances. The outcome of such activities costs more than they actually bring. Secondly, the changes cannot be applied fast enough to satisfy the customers’ needs.",[109,216,218],{"id":217},"category-page-ads","Category Page Ads",[11,220,221],{},"Targeting traffic via ads is another option of how to increase conversion rates. If done correctly it can bring a significant increase. On the other hand, the actual return on the investment is lower, taking the ad spent into consideration.",[23,223,225],{"id":224},"how-to-optimize-category-pages-deliver-better-results","How to optimize category pages & deliver better results",[11,227,228],{},"The optimization of category pages can be crucial in getting more website traffic, converting it to sales, and creating loyal customers from first-time shoppers. It is important to provide a valuable digital experience. When the category page doesn’t deliver what the customers expected, they leave without a purchase, not finding what they wanted. Relevancy is what matters. A crucial prerequisite to any calculation is historical data on products, sales, segments, etc. Without enough data, the results cannot be as satisfying.",[75,230,232],{"id":231},"personalization-and-product-recommendations","Personalization and product recommendations",[11,234,235],{},"The category pages need to be personalized to be able to achieve different goals for different segments. Adding a layer of personalization to different audiences’ levels up simple segmentation and yields higher returns. With first-time customers, you will probably focus on conversion rate while with loyal customers you can highlight a particular brand based on brand affinity, new products to complement already purchased ones, or something a little more diverse, depending on the customer profile. Assigning different products to each segment, based on the customer’s behavior on-site increases customer engagement. Tracking how the customer acts on the websites helps to understand their needs and display relevant items. If two people are looking for backpacks, they might be looking for a different kind. If one person is shopping for notepads, writing supplies, it is likely they will also need a school backpack. A different customer is looking at hiking boots and camping gear and might need a hiking backpack.",[11,237,238],{},[70,239],{"alt":72,"src":240},"\u002Fupload\u002Fproduct-recomendation-illustration.jpg",[109,242,244],{"id":243},"sorting","Sorting",[11,246,247],{},"Sorting products on the site in specific order or sequence based on their attributes, performance metrics, and their combination. The attributes can be price, size, brand, availability, etc. Metrics can be, for example, conversion rate, margin, revenue per impression, or inventory information. Attributes and metrics rely on the data about the products and the customers, collected from the website and internal databases. By adjusting the weights of the values, it is possible to promote and demote products in the sequence causing the relocation of the product on the page.",[109,249,251],{"id":250},"highlighting","Highlighting",[11,253,254],{},"Choosing to highlight specific products or groups of products, seasonal or campaign offers at the top of the category page supports marketing efforts. Placing some products on the most engaging and prominent spots on the sites creates a store-like experience. It is commonly used to promote new products, collaborations, and ranges. Highlighting can work for limited offers (discounts or weekend sales) and display products for a certain time period. Scheduling this should be aligned with marketing campaigns. Another option to adjust highlighting can be based on different business goals, chosen metrics, like profitability or liquidity.",[109,256,258],{"id":257},"segmentation","Segmentation",[11,260,261],{},"Segmenting your customers should happen on top of sorting and highlighting products. It allows creating category pages with specific product sequences that vary among different audiences. The marketing approach differs by different types of customers, their preferences, affinity, and different shopping stages, therefore category pages should be aligned with that as well.",[109,263,265],{"id":264},"personalization","Personalization",[11,267,268],{},"Showing the customers what they want to buy, the right time, the right product – like a personal shopper. It helps customers to discover items they really want. In e-commerce, personalization has a more significant impact and is an important part of modern shopping. It provides relevant recommendations for the particular customer segment (or with advanced algorithms, even down to each individual customer). Personalization creates an experience based on the customer’s behavior.",[23,270,272],{"id":271},"using-machine-learning-for-relevant-product-displaying","Using Machine Learning for relevant product displaying",[11,274,275],{},"Powering product recommendation with Machine learning allows you to be dynamic and automatically adapt to the changes. What customers want to see is what they really need, ideally on the very first page. Long searching is demotivating. Using historic purchases, similar customer behavior, or other factors can significantly change the way your customers interact with your e-shop.",[75,277,279],{"id":278},"product-ranking-based-on-customers-behavior-and-other-factors","Product ranking based on customers behavior and other factors",[11,281,282],{},"Product ranking in a sense of algorithms is a process of product scoring based on what the customers like. Additionally, the score can be evaluated based on the factors the e-shop defines, for example, storage availability (the more pieces of each product you have and need to sell, the higher score it gets). What we have found as an effective method is to look more deeply and find the optimal combination of the products display next to each other. Our procedure usually consists of data integration from various systems, followed by advanced analytics and machine learning algorithms for continual improvement.",[284,285,286],"note",{},"\nTo understand what product ranking is, think of it as product ranking from the system perspective, not as customer review. The ranking that you calculate helps the algorithm to show the right products on the category page.\n",[75,288,290],{"id":289},"testing-and-optimization","Testing and optimization",[11,292,293],{},"Finding an optimal solution isn’t an easy task, especially when personalization and merchandising are dynamic, evolving processes requiring repetition, calculation, and testing. AB Testing is a great approach for detecting the most profitable adjustments. It helps to discover the performance of different category pages or the effectiveness of product highlighting. It allows you to test competing strategies and make informed decisions for elevated results. It is possible to test a whole customer base or just a smaller part. With testing on different groups, you can experiment with bold ideas. You can see if sorting by high converting products is better than sorting by high-profit products. Or, you can assess if personalization delivers higher results than no personalization on category pages.",[75,295,297],{"id":296},"continuous-improvement","Continuous improvement",[11,299,300],{},"Once you set up the algorithms for relevant product displaying, you are not done yet. It is only a first step but not the last. Actually, the process is evolving, and you cannot stay static. Sometimes the results are oversimplified or too generalized, and you need to use more contextual data to improve the relevance. Thinking of it in the context of the customer journey helps to maintain the dynamics within the product associations.",[23,302,304],{"id":303},"what-to-think-about-before-diving-in","What to think about before diving in",[11,306,307],{},"Are you hooked yet? Ready to dive your e-commerce business into the ocean of personalization? Slow down a little bit. There are a few things to think about before you do any action.",[309,310,311,321,327,335,343,351],"ul",{},[312,313,314,317,320],"li",{},[18,315,316],{},"Make sure your website is ready!",[318,319],"br",{},"Some technology can decrease performance. Even if the personalization is great, it should not be implemented if the usability is diminished.",[312,322,323,324,326],{},"**Don’t change the entire website!",[318,325],{},"\n**Structural elements cannot be personalized, they should remain the same (cart, navigation panel, etc.)",[312,328,329,332,334],{},[18,330,331],{},"Less is more!",[318,333],{},"Too much of everything is confusing, too dynamic can be misleading. The key is not to look at personalization.",[312,336,337,340,342],{},[18,338,339],{},"Prepare your data!",[318,341],{},"Before you start the analyses and evaluations, gather all relevant data, the more historic data the better.",[312,344,345,348,350],{},[18,346,347],{},"Identify key factors!",[318,349],{},"Figure out, how you want to score\u002Frank\u002Frecommend the content. Do you need to clear your warehouse or promote more trendy items? What about seasonal stuff? Segmented or more individualized? More factors and segments, the more complicated and expensive it gets.",[312,352,353,356,358],{},[18,354,355],{},"Start small!",[318,357],{},"Try only a few changes first, test them, and then you can see if it is worth it to advance or not.",[23,360,362],{"id":361},"summary","Summary",[11,364,365],{},"Successful category pages drive performance and contribute to growing conversion and return ratios. Optimizing them generates a competitive advantage and brings multiple benefits to your e-commerce business and customers.",[309,367,368,371,374,377,380],{},[312,369,370],{},"Resource savings with automatization",[312,372,373],{},"Better performance with category pages optimization",[312,375,376],{},"Relevant experiences with personalization",[312,378,379],{},"Achieving more than one target with optimization and testing",[312,381,382],{},"Easy to scale with a growing product portfolio",[11,384,385],{},"It may seem super easy, just to set up a few rules and you are good to go. However, working with a large amount of data and continuous training of the algorithms is tricky. Rather than DIY everything, cooperating with more experienced professionals prevents the risk of “breaking it all” and losing your customers to it.",[11,387,388,389,392],{},"We have effectively set up the product ranking and relevant recommendations on category pages for many of our clients and helped them to ",[18,390,391],{},"achieve a 15-27% increase"," in the conversion only a few weeks after implementing the solution. We have been able to customize the solution based on different business needs and continuously improve the solution thanks to testing.",[132,394,396],{"link":134,"button":395},"Contact Us","\nCome to us today and help your customers to find the desired item tomorrow.\n",{"title":72,"searchDepth":157,"depth":157,"links":398},[399,400,403,408,409],{"id":203,"depth":157,"text":204},{"id":224,"depth":157,"text":225,"children":401},[402],{"id":231,"depth":163,"text":232},{"id":271,"depth":157,"text":272,"children":404},[405,406,407],{"id":278,"depth":163,"text":279},{"id":289,"depth":163,"text":290},{"id":296,"depth":163,"text":297},{"id":303,"depth":157,"text":304},{"id":361,"depth":157,"text":362},"Company","\u002Fupload\u002Fcategoryranking-article-cover.webp",{},"\u002Fen\u002Fblog\u002Fincrease-conversions-with-category-page-product-ranking","2020-11-06T10:10:50.000+00:00",9.12,"10 min read",[418,419],"content\u002Fen\u002Fblog\u002Fgetting-the-most-out-of-permission-marketing.md","content\u002Fen\u002Fblog\u002Fmachine-learning-in-marketing-practice.md",{"title":188,"description":193},"en\u002Fblog\u002Fincrease-conversions-with-category-page-product-ranking","Online market is becoming very saturated and crowded with hundreds of e-shops, and the number is increasing. To keep up with the competition, every internet store must create a unique approach, provide enjoyable shopping and know its customers.","jo4l7QC10gq9zQLNdkKbEgxJz9GV44x0803c8Kv8BkM",{"id":425,"title":426,"author":6,"body":427,"category":6,"description":431,"extension":168,"image":794,"isToc":170,"langAlt":6,"meta":795,"metaDescription":6,"navigation":172,"path":796,"published":172,"publishedAt":797,"readingTimeMinutes":798,"readingTimeText":799,"relatedArticles":800,"seo":801,"stem":802,"teaser":803,"updatedAtCustom":6,"__hash__":804},"blog_en\u002Fen\u002Fblog\u002Fpractical-use-of-cognitive-computing.md","Practical use of Cognitive Computing",{"type":8,"value":428,"toc":780},[429,432,435,439,442,445,449,460,463,466,471,474,477,480,485,488,494,500,503,533,536,540,543,546,551,554,559,562,567,572,576,579,585,588,595,600,603,614,620,628,631,636,640,643,648,652,655,659,662,667,674,679,686,697,700,704,707,713,718,721,725,732,737,741,752,757,764,769,771,774,777],[11,430,431],{},"If you combine artificial intelligence with signal processing, you can improve everyday tasks such as safety equipment checks, anomaly detection, or reading documents. Technology incorporating machine learning, natural language processing, human-computer interaction, and more are described as cognitive computing. At the first sight, it may seem like too much science behind, yet the algorithms can be implemented easier than you might think and help you with your marketing or occupational safety within your business.",[11,433,434],{},"We started the practical part of the workshop with an overview of the areas of Azure Cognitive Services and then we moved to use cases of Anomaly Detector, text, and vision services.",[75,436,438],{"id":437},"azure-cognitive-services","Azure Cognitive Services",[11,440,441],{},"Before we explain the practical use of Azure Cognitive Services, introducing all areas can give a good picture of how technology collaboration and accessibility can create an empowering experience for the end-user.",[11,443,444],{},"Azure Cognitive Services is a set of machine learning algorithms developed to solve problems in the field of Artificial Intelligence (AI). They are available widely to developers without requiring machine-learning expertise. All it takes is an API call to embed the ability to see, hear, speak, search, understand, and accelerate decision-making. It is a package of 25 tools that through APIs allow the developers to add a variety of features to their applications.",[23,446,448],{"id":447},"part-1-anomaly-detector","Part 1| Anomaly Detector",[11,450,451,452,455,456,459],{},"In the first part Azure Cognitive Services demos in practice, we focused on the ",[18,453,454],{},"Anomaly Detector"," service and ",[18,457,458],{},"AML Notebooks",".",[11,461,462],{},"In general, the anomaly detection algorithm predicts the value at a selected point based on previous observations. This prediction always has a certain sensitivity\u002Fconfidence interval in which it moves (light blue area in the image below).",[11,464,465],{},"The predicted value is then compared to the actual measured value and the points at which it is actually measured are identified.",[11,467,468],{},[70,469],{"alt":72,"src":470},"\u002Fupload\u002Fvalue-prediction.webp",[11,472,473],{},"The Azure anomaly detector REST API is a service that provides the ability to detect anomalies in time series from any data source. The only condition is that the data must be in a defined structure: timestamp + selected value",[11,475,476],{},"The Rest API can be called from any tool that can call GET requests. Examples include Jupyter Notebooks, Postman, Visual Studio, or Azure-enabled services such as Databricks, or Azure Machine Learning with integrated notebooks.",[11,478,479],{},"Azure anomaly detection REST API is a service provided by Azure as one of the Cognitive services accessible via the Azure portal where you can obtain the authorization key and endpoint that are necessary for later calls. The output after calling this API is a set of parameters that say whether it is an anomaly at a given point in time and whether it was a decrease or an increase.",[11,481,482],{},[70,483],{"alt":72,"src":484},"\u002Fupload\u002Fdata-manipulation-2.webp",[11,486,487],{},"Azure anomaly detector REST API works in two optional modes.",[11,489,490,493],{},[104,491,492],{},"\"Last\""," mode Works on stream data. Each point in time is analyzed based on a model trained by previous data. For example, it is suitable for data from Google Analytics.",[11,495,496,499],{},[104,497,498],{},"\"Entire\""," mode creates and trains one model for the entire time series and detects anomalies over the entire model and all data points at once.",[11,501,502],{},"Anomaly detection can be configured by entering parameter values in the request. We have the ability to work with these parameters:",[309,504,505,511,514,520,526],{},[312,506,507,510],{},[104,508,509],{},"Sensitivity - \"Sensitivity\""," is from 0 to 99, defines how sensitively the back-end API detects anomalies",[312,512,513],{},"Granularity - It can be annual, monthly, weekly, daily, hourly, minute (data must correspond to this granularity, i.e. the difference between subsequent data points must correspond to this Period)",[312,515,516,519],{},[104,517,518],{},"CustomInterval"," - For cases of different granularity (e.g. customInterval = 5 & granularity = minute will have an interval of 5 minutes)",[312,521,522,525],{},[104,523,524],{},"Period"," - defines how many history points are used to detect current anomalies. The extent of the period will vary according to the granularity.",[312,527,528,529,532],{},"maxAnomalyRatio - \"",[104,530,531],{},"MaxAnomaly","\" defines the maximum percentage of anomalies in one detection.",[11,534,535],{},"We also talked about the use of the Anomaly detector REST API in the event of an error in the implementation of measurement on the web.",[75,537,539],{"id":538},"business-case-fooled-bidding-engine","Business Case – Fooled bidding engine",[11,541,542],{},"Let’s look at one of our client’s normal day, an e-shop that sells clothes and uses a bidding engine to place ads. If everything works by default, the customer sees the advertisement, comes to the website, and makes an order.",[11,544,545],{},"Information about a successful order is sent to the bidding engine, which optimizes its behavior based on it. Unfortunately, not all days are so exemplary.",[11,547,548],{},[70,549],{"alt":72,"src":550},"\u002Fupload\u002Fnormal-day.webp",[11,552,553],{},"Unfortunately, a new version of the site was published from the test environment, which contained a measurement error that caused a duplication of pageviews to be measured for the men's sweatshirt category, indicating a successful conversion. This caused the bidding engine to start receiving false information and to make bad decisions because it thought the men's sweatshirt ad is twice as successful as it actually is. The engine started investing higher amounts in the ad. If this error would not be caught in time, it could lead to large losses in the marketing budget.",[11,555,556],{},[70,557],{"alt":72,"src":558},"\u002Fupload\u002Fbug-1.webp",[11,560,561],{},"In order to detect an anomaly, it is necessary to have a specialist who would check the data regularly and would be sufficiently attentive to changes in the data. It may not be as easy as noticing the mistakes in this case (in Google Analytics, only a week is visible by default).",[11,563,564],{},[70,565],{"alt":72,"src":566},"\u002Fupload\u002Fanomaly-detection-1.webp",[11,568,569],{},[70,570],{"alt":72,"src":571},"\u002Fupload\u002Fanomaly-detection-2.webp",[75,573,575],{"id":574},"solution-detecting-anomalies","Solution - Detecting Anomalies",[11,577,578],{},"Such a fluctuation in the measured data can be detected with Azure Anomaly Detector. There are two options.",[109,580,582],{"id":581},"azure-ml",[18,583,584],{},"Azure ML",[11,586,587],{},"One option is to use the Azure Machine Learning tool using integrated notebooks. Among other things, this tool allows you to create and manage models for machine learning.",[11,589,590,591,594],{},"We integrated this tool into the standard e-commerce process. Data for anomaly detection were obtained from the web analytics system in the standardized format ",[104,592,593],{},"Timestamp, Value",". We analyzed the data by calling the Azure anomaly detector API, and if we detect a problem, we start fixing it immediately.",[11,596,597],{},[70,598],{"alt":72,"src":599},"\u002Fupload\u002Fdata-manipulation.webp",[11,601,602],{},"However, this particular solution comparing to similar tools can be challenging due to:",[309,604,605,608,611],{},[312,606,607],{},"Need for regular manual execution - Someone needs to run the code regularly",[312,609,610],{},"The necessity to have relatively advanced knowledge of some programming language such as Python",[312,612,613],{},"Not completely clear insights, it is necessary to further modify, visualize, etc.",[109,615,617],{"id":616},"waaila",[18,618,619],{},"Waaila",[11,621,622,623,459],{},"The second option, which eliminates the problems described above, is to use ",[143,624,627],{"href":625,"rel":626},"https:\u002F\u002Fwaaila.com",[147],"the Waaila app",[11,629,630],{},"Waaila's connection to the standard data processing system is similar to the previous solution. We can connect directly to the data in GA through it. It is then possible to perform various tests on these data using logical conditions. In our case, we defined data in the format Timestamp: pageviews. Then the Azure anomaly detector API is called, and we find out if there is an anomaly in the dataset.",[11,632,633],{},[70,634],{"alt":72,"src":635},"\u002Fupload\u002Fwaaila-azure-anomaly-detector.webp",[75,637,639],{"id":638},"why-is-the-waaila-app-different","Why is the Waaila app different",[11,641,642],{},"The result obtained through Waaila has a clear and simple form. In the output table, we can see the days on which the anomaly was detected. These are the days that followed the publication of a new version of the website containing a measurement error. We can see that on both days there was a positive anomaly, which means that the display of the confirmation page was more frequent than was predicted based on previous developments.",[11,644,645],{},[70,646],{"alt":72,"src":647},"\u002Fupload\u002Fwaaila-demo.webp",[23,649,651],{"id":650},"part-2-azure-cognitive-services-text-vision","Part 2 | Azure Cognitive Services – Text & Vision",[11,653,654],{},"The second part of the workshop contained examples of the Text and Vision group of Cognitive services. One of the most common use cases involves the Vision group of Cognitive Services. We meet frequently with companies who experience troubles with employee safety obedience and are looking for a more sophisticated solution. The second case focuses on text recognition, for instance, homework check automation or reading receipts. Third case comments on means to gather data about customer satisfaction.",[75,656,658],{"id":657},"business-case-1-safety-equipment-check","Business Case 1: Safety Equipment Check",[11,660,661],{},"Construction companies are required to check that all workers on their sites wear hard hats and reflective vests. However, this is costly in terms of time and human resources. To minimize this cost, companies can incorporate an AI solution using the Custom Vision service in order to detect the equipment automatically.",[11,663,664],{},[70,665],{"alt":72,"src":666},"\u002Fupload\u002Fsafety-equipment-recognizing.webp",[11,668,669,670,673],{},"Using this approach, when somebody enters the construction site, the security camera at the entrance sends their image to be processed using the ",[18,671,672],{},"Custom Vision"," service. The image is evaluated for the presence of safety equipment based on a pre-trained model of similar tagged images. The results of the evaluation are sent back and in case of missing equipment, a message is outputted.",[11,675,676],{},[70,677],{"alt":72,"src":678},"\u002Fupload\u002Fcognitive-services-camera.webp",[11,680,681,682,685],{},"The visual evaluation can be combined with customized and personalized messages to be more noticeable and thus a better warning for workers without the safety equipment. The customized messages can be created in real-time using the ",[18,683,684],{},"Text to Speech"," service. This service constructs a voice message from inputted text using a high variety of voices in over 45 languages (including the Czech language).",[11,687,688,689,692,693,696],{},"Moreover, to personalize the warnings, ",[18,690,691],{},"Face verification"," can be used to compare the image of entering workers with database workers' photos. Based on the extracted name, a personalized message can be constructed again using the Text to Speech service. ",[18,694,695],{},"The personalized messages have the highest impact"," on ensuring that workers wear the safety equipment, especially if combined with the possibility to report the outcome to the supervisor.",[11,698,699],{},"This AI solution to automatic check allows the companies to save human and financial resources while minimizing the risk of having to pay a fine for potentially incorrect safety equipment on the site.",[75,701,703],{"id":702},"business-case-2-automatic-evaluation-of-exercise-results","Business case 2: Automatic evaluation of exercise results",[11,705,706],{},"AI is very useful in areas where documents were not fully converted to electronic form yet. When the current Covid-19 pandemic closed schools, teachers were often limited by the fact that their teaching materials were not well equipped for distance learning. Correcting homework in exercise books distantly requires a series of printing and scanning, costing a high amount of time and other resources. This opens a possibility for the AI solution using a Form Recognizer.",[11,708,709,712],{},[18,710,711],{},"Form Recognizer"," allows you to automatically extract both printed and hand-written text from computer non-readable documents and images. You provide training files and select one of the available approaches. The first approach consists of optimized prepared models for receipts and business cards, however, these cannot be applied to other documents. The second approach allows extracting all text fields that can be viewed as key-value pairs. While this provides more flexibility than the first approach, you cannot select which part of the file to concentrate on and cannot extract values without a well-located key. Most flexible and thus most suited for the case of school material is the third approach which consists of labeling required text fields and training on thus labeled files. For labeling, there is a special online tool where you can create labels and interactively assign them to OCR-extracted text fields from your training files. For illustration, we labeled and trained a simple model on a page from a first-grade mathematics textbook. Below is a snapshot of information extracted based on the simple model, displayed both visually in colored rectangles and as a list of values assigned to the tags of matching color along with a confidence of the assignment.",[11,714,715],{},[70,716],{"alt":72,"src":717},"\u002Fupload\u002Flabellingtool.webp",[11,719,720],{},"Using the Form Recognizer you can construct automatic homework evaluation by collecting a sample of homework, labeling the required fields on the sample, and training the model. Then you can use this model to form automatic extraction of the required information from other files and comparison of the extracted values to a solution key. While this is too demanding for a single teacher, it opens a business opportunity to cooperate with a publishing house on providing an official solution thus helping distance teaching.",[109,722,724],{"id":723},"applications-of-form-recognizer","Applications of Form Recognizer",[11,726,727,728,731],{},"Form Recognizer is useful in many fields. For example, when a customer brings ",[729,730,143],"del",{}," receipt for purchased goods he wants to complain about, the cashier needs to retype the receipt to fill in the complaint. Alternatively, in a loyalty program when the producer company requires invoices from distributors as proof for distributing the products, they often receive the forms in a scan or even paper form that they need to digitalize. To sum up, Form Recognizer saves both time and other resources. Based on our experience, it can provide even better results than manual extraction as the people working on it may often be over-worked or not well informed.",[11,733,734],{},[70,735],{"alt":72,"src":736},"\u002Fupload\u002Fcontoso-receipt-2-information.webp",[75,738,740],{"id":739},"business-case-3-customer-satisfaction","Business case 3: Customer satisfaction",[11,742,743,744,747,748,751],{},"Information about customer satisfaction is necessary for improving the quality of goods and services and keeping customers from going to the competition. It is mostly gathered from surveys and a set of buttons with smiley faces, however, these provide not only under-represented but also skewed results due to the selection of people willing to answer it. To overcome this problem, companies can employ behavior analytics on the e-shop and perceived emotion recognition in the stores. The e-shop ",[18,745,746],{},"Text Analytics"," service can help process comments and chat messages to prevent customers from leaving due to negative experiences or negative impressions of one customer to spread to other customers. At this moment there is only a selected number of language options for the TextAnalytics but it can be paired with ",[18,749,750],{},"Translator"," service to cover other languages. The text extraction can be combined with an analysis of customers' paths, waiting times, and other behavioral patterns which may provide further information on satisfaction.",[11,753,754],{},[70,755],{"alt":72,"src":756},"\u002Fupload\u002Fsatisfaction_buttons.webp",[11,758,759,760,763],{},"In stores, instead of using the buttons to express satisfaction, companies can use the entrance cameras to take an image. The image is then processed using a part of the ",[18,761,762],{},"Face"," service that can evaluate the Perceived emotion recognition. In this recognition, the location of the face in the image is found and several emotions are searched for in the detected face to evaluate the degree to which they are recognizably present on the face. This can be then used to find out how happy was a customer when leaving or how much did his mood change while inside the store which can help with the optimization of the store and the services.",[11,765,766],{},[70,767],{"alt":72,"src":768},"\u002Fupload\u002Fmona-lisa-and-emotions.webp",[23,770,362],{"id":361},[11,772,773],{},"To summarized the workshop focused on Cognitive Computing and its practical applications, we showed and explain a few use interesting cases for everyday use. With Azure, you can not only ensure security but also it can be very easily connected to cloud storage and other tools that overall create one well-working and inter-connected environment, built for your convenience.",[11,775,776],{},"We have applied similar and many more solutions. Marketing combined with Data Science experience and technical expertise provides us with a competitive advantage to build custom solutions for each project.",[11,778,779],{},"Let us know, how we can help you grow.",{"title":72,"searchDepth":157,"depth":157,"links":781},[782,783,788,793],{"id":437,"depth":163,"text":438},{"id":447,"depth":157,"text":448,"children":784},[785,786,787],{"id":538,"depth":163,"text":539},{"id":574,"depth":163,"text":575},{"id":638,"depth":163,"text":639},{"id":650,"depth":157,"text":651,"children":789},[790,791,792],{"id":657,"depth":163,"text":658},{"id":702,"depth":163,"text":703},{"id":739,"depth":163,"text":740},{"id":361,"depth":157,"text":362},"\u002Fupload\u002Fcognitive-computing-reading-cover.webp",{},"\u002Fen\u002Fblog\u002Fpractical-use-of-cognitive-computing","2020-10-27T10:26:29.000+00:00",12.47,"13 min read",[419],{"title":426,"description":431},"en\u002Fblog\u002Fpractical-use-of-cognitive-computing","Recently, we organized another online workshop on the topic of AI. This time we looked at use cases of Cognitive Computing. ","AAut8oZN3FCBWFH2JAa6ITI8JbP2EP969gnqYOr6P9w",{"id":806,"title":807,"author":6,"body":808,"category":6,"description":812,"extension":168,"image":982,"isToc":170,"langAlt":6,"meta":983,"metaDescription":6,"navigation":172,"path":984,"published":170,"publishedAt":985,"readingTimeMinutes":6,"readingTimeText":6,"relatedArticles":6,"seo":986,"stem":987,"teaser":988,"updatedAtCustom":6,"__hash__":989},"blog_en\u002Fen\u002Fblog\u002Fquick-trip-beyond-data-quality.md","Quick trip beyond data quality",{"type":8,"value":809,"toc":971},[810,813,816,819,823,826,831,834,838,841,845,848,852,855,859,862,866,869,872,876,879,905,909,912,917,921,924,933,937,950,954,963,965,968],[11,811,812],{},"Especially if the core business derives from online transactions. Applications of a data-driven approach unfold new opportunities across various disciplines, eloquently in marketing, that positively impact the company's success. All the efforts may just be vain, even counterproductive when the data is imprecise. The key can be found in data quality measurement followed by data quality management.",[11,814,815],{},"Today, the data revolution is encountering massive data acquisition, and repurposing to support analyses, justifying broader insights on data quality validation as a new important business component. It is impacting aspects such as regulatory compliance, customer satisfaction, and, of course, the accuracy of decision making. Warranting high-quality data is essential to achieve its true purpose.",[11,817,818],{},"Simply, data quality is the ability of the data to serve its intended purpose, whereas poor data quality prevents from achieving appointed goals. Obtaining such high-quality requires improving data strategy along with implementing measurements to verify its effectiveness.",[23,820,822],{"id":821},"data-quality-characteristics","Data quality characteristics",[11,824,825],{},"The quality is often being assessed on six core dimensions:",[827,828,830],"h5",{"id":829},"_1-completeness","1. Completeness",[11,832,833],{},"Required data is complete and available. Completeness in the meaning for comprehensive the information is. If the data is not complete it may not be usable.",[827,835,837],{"id":836},"_2-uniqueness","2. Uniqueness",[11,839,840],{},"Data is unique when there is no data duplicity in the records, as that could lead to a risk of outdated data.",[827,842,844],{"id":843},"_3-accuracy","3. Accuracy",[11,846,847],{},"Data accuracy means that the information is correct if it reflects reality. This data characteristic is crucial because when the data is not accurate it can cause dramatic problems with severe impact.",[827,849,851],{"id":850},"_4-consistency","4. Consistency",[11,853,854],{},"Consistent data is particularly crucial when aggregating data from multiple sources, internal and external. Data consistency refers to consistency in variables and measurement, meaning the data is the same for all instances of an application.",[827,856,858],{"id":857},"_5-timeliness","5. Timeliness",[11,860,861],{},"Data needs to be up to date in order to support good business decisions. The fresher data is, the more trustworthy it is and the reactions are more relevant. Out-of-date data causes wasting money and other resources.",[827,863,865],{"id":864},"_6-validity","6. Validity",[11,867,868],{},"To ensure the data is compliant with policies and requirements, it needs to be valid or validated. Thus, it can be correct and accurate",[11,870,871],{},"It is beneficial to assess all the dimensions on all channels and from all ends to ensure the best outcome possible, which entails significant technical knowledge. And there is much more to it, than simple data to error ratio, or more difficult than just cleaning the dark data.",[23,873,875],{"id":874},"the-most-common-problems-in-data-quality","The most common problems in data quality",[11,877,878],{},"Companies often overlook data quality without even knowing the impact. However, even the small gap can disrupt the whole analysis or measurement. The errors commonly create misleading conclusions, causing troubles on all ends. Low data quality can be caused by a number of problems occurring in the process:",[309,880,881,884,887,890,893,896,899,902],{},[312,882,883],{},"Unreliable data",[312,885,886],{},"Incomplete data",[312,888,889],{},"Duplicated data",[312,891,892],{},"Ambiguous interpretation",[312,894,895],{},"Inconsistent formats",[312,897,898],{},"Accessibility",[312,900,901],{},"Late data entry",[312,903,904],{},"Outdated information",[23,906,908],{"id":907},"data-as-a-foundation-for-accurate-decisions","Data as a foundation for accurate decisions",[11,910,911],{},"Data-driven decision making is a competitive advantage. High-quality data creates a foundation and directly impacts business outcomes. If the data is in poor quality, the decisions cannot be accurate, which influences the entire business performance and may lower the profit.",[11,913,914],{},[70,915],{"alt":72,"src":916},"\u002Fupload\u002Fdata-quality-pyramid.webp",[23,918,920],{"id":919},"our-solutions-to-achieve-higher-data-quality","Our solutions to achieve higher data quality",[75,922,148],{"id":923},"measurement-hub",[11,925,926,927,932],{},"One way of dealing with such problems is implementing tested and verified solution ",[143,928,930],{"href":145,"rel":929},[147],[18,931,148],{},". It ensures the correct measuring and validation of website data, averts errors, and missing information. Thanks to its specified configuration of a data layer above a website, the data is consistent and readable for all marketing, analytical, and communication platforms, resulting in improved data quality. Measurement Hub exploits Google Tag manager extensively by advanced settings of tags, triggers, and variables. It also provides data profiling, combining website data with data from CRM and internal systems. Consequently, the marketing approach jumps to a higher level.",[75,934,936],{"id":935},"waaila-tracking-validator","Waaila Tracking Validator",[11,938,939,940,946,949],{},"In order to utilize data for analyses and subsequent activation, from analytical and marketing platforms, the initial input needs to be high-quality and correct as well as remain consistent throughout the whole process. When the data layer is programmed, it might contain many unspotted mistakes that are generating severe errors and it can be tricky to find them, especially for non-developers. With ",[143,941,944],{"href":942,"rel":943},"https:\u002F\u002Fwaaila.com\u002Fen\u002Ftracking-validator",[147],[18,945,936],{},[18,947,948],{},","," an extension for Google Chrome, the data layer is being monitored and validated semi-automatically, for syntax and semantic errors, showing inconsistencies to address the issues and solve them quickly.",[75,951,953],{"id":952},"waaila-app","Waaila App",[11,955,956,957,962],{},"As data is not static but rather dynamic, maintaining its quality requires continual attention, usually done manually, which turns it into a separate goal instead of means. And the time and resource savings, that initially drove the quality project, are being wasted once again. With automatization, the quality of data can be tested within minutes, even periodically on the background. ",[143,958,960],{"href":625,"rel":959},[147],[18,961,619],{}," web application is designed to discover web data anomalies and inconsistencies on time, which prevents possible failures, resulting in improved marketing strategies. Overall, it is much less demanding and less costly to prevent the data issues from emerging then fixing them while burning.",[23,964,127],{"id":126},[11,966,967],{},"In summary, data establishes the foundation of a healthy and prosperous business. Explicitly e-commerce derives most benefits from high-quality data utilization and data quality measurement. For many companies, managing quality data may seem like an overwhelming task. It necessitates right recourses, processes and experience; accurate definition of requirements, carefully designed data architecture, sustainable administration, and reliable control systems.",[132,969,970],{"link":134,"button":395},"\nWe house highly skilled professionals in this specific part of the data field. Let us help you acquire the high-quality data you need!\n",{"title":72,"searchDepth":157,"depth":157,"links":972},[973,974,975,976,981],{"id":821,"depth":157,"text":822},{"id":874,"depth":157,"text":875},{"id":907,"depth":157,"text":908},{"id":919,"depth":157,"text":920,"children":977},[978,979,980],{"id":923,"depth":163,"text":148},{"id":935,"depth":163,"text":936},{"id":952,"depth":163,"text":953},{"id":126,"depth":157,"text":127},"[object Object]",{},"\u002Fen\u002Fblog\u002Fquick-trip-beyond-data-quality","2020-04-29T12:00:00.000+00:00",{"title":807,"description":812},"en\u002Fblog\u002Fquick-trip-beyond-data-quality","In this digital world, when data analyzing is becoming a necessity for many organizations to stay on top, data quality is crucial for continuous prosperity and competitive advantage. ","_mkWXHCmhcfXCdpQQnw_N9OV9Q5983O-6dvSFAZoE1w",1789131823072]