Mar 21, 2023 982 reads

What is GDPR? Is GA4 GDPR Compliant?

Data privacy has become increasingly important in recent years. This is due to consumers’ and users’ concerns about protecting their personal data and governments enacting various laws to safeguard that data. In this article, we’ll focus on Google Analytics 4’s (GA4) data privacy features and examine whether these features comply with the General Data Protection Regulation (GDPR).What Is GDPR?GDPR (General Data Protection Regulation) is a data privacy regulation that came into effect in 2018. It governs how organizations in the European Union collect, process, and store personal data. GDPR adopts a user-centric approach to privacy, requiring organizations to explain what data they collect, how they use it, and with whom they share it.Whom Does GDPR Cover?GDPR sets standards for processing personal data in the EU and the European Economic Area (EEA), establishing principles of transparency, fairness, purpose limitation, accuracy, integrity, and confidentiality.All companies operating within the EU or EEA must comply with GDPR when processing personal data. Moreover, any company outside the EU/EEA that handles personal data of EU/EEA residents must also adhere to GDPR rules.For example, an EU citizen visiting Turkey as a tourist falls outside GDPR’s scope while abroad. Conversely, a non-EU citizen in an EU country is protected under GDPR. If a U.S. citizen visits Germany, German organizations must handle that person’s data in compliance with GDPR, even though the individual is not an EU citizen.Does GDPR Apply in the U.K.?GDPR took effect in the U.K. in May 2018. After Brexit, the U.K. incorporated GDPR into its own Data Protection Act, maintaining equivalent protections for personal data.History of Privacy Fines Against Google AnalyticsGDPR has empowered data subjects with greater control over their personal information. Since its enforcement on May 25, 2018, Google has faced significant fines under GDPR. In March 2020, Sweden fined Google LLC €7 million for violating Article 17(1)(a) by not removing search results upon request. Then in December 2021, France’s CNIL fined Google €150 million because users could not refuse tracking cookies as easily as they could accept them. Google Ireland was fined €60 million, and Google LLC €90 million for the same issue.French regulators also rejected GA4’s IP-anonymization as insufficient to protect data transferred to the U.S. The EU Court of Justice in July 2020 invalidated the Privacy Shield framework governing EU-U.S. data transfers, further complicating Google’s ability to move EU data to its U.S. servers.Other data protection authorities in Austria, the Netherlands, and Norway have similarly found Google Analytics non-compliant with GDPR, threatening fines or restrictions.What Is Personally Identifiable Information (PII)?PII refers to any data that can identify an individual—name, address, birthdate, phone number, email, national ID, passport number, etc. Protecting PII is critical because its exposure can reveal someone’s identity and personal details.GA4’s User Privacy FeaturesGoogle Analytics 4 offers several privacy-focused settings, allowing site owners to honor user consent while still gaining useful insights. Two key areas under Data Settings are Data Collection and Data Retention. Let’s explore them.Data Collection SettingsYou can access Data Collection under Admin > Data Settings > Data Collection:Google Signals Enabling Google Signals allows GA4 to link signed-in users’ site/app data with their Google accounts, provided they’ve consented to ad personalization. Signals lets you use location, search, YouTube, and partner-site data in aggregate, anonymized reports. Users can manage this via myactivity.google.com.Location & Device DataTurning on these options lets Analytics collect geographic and device information, with the ability to exclude specific countries.User Data Collection ConsentHere, you confirm that your site/app informs users how their data will be collected and shared with Analytics, and that you’ve obtained their consent accordingly.Data Retention SettingsData Retention lets you choose how long user-level and event-level data are kept (2 or 14 months). You can also reset user data on each new session. Your choice should reflect your industry’s needs and the sensitivity of the information collected.IP AnonymizationGA4 anonymizes the last 8 bits of each user’s IP address by default, fully embedding anonymization in its data model. This protects users’ privacy while still providing geographic and device insights needed for analysis.Consent ModeWhen users deny cookie consent, your Analytics data will be incomplete. Consent Mode uses machine learning to model those users’ behavior based on similar consenting users, preserving privacy while retaining useful insights in your reports.Server Location & Data Transfer Restrictions in GA4Under GDPR, transferring personal data from the EEA or U.K. to outside jurisdictions without adequate safeguards is restricted. GA4 users cannot choose where their data is stored—much of Google’s infrastructure is in the U.S. If you process EU/U.K. personal data in GA4, you must ensure compliant transfer mechanisms are in place, often requiring legal consultancy.

Feb 22, 2023 2394 reads

What are the differences between UA and GA4?

In this article, we examined the working principles of Universal Analytics and Google Analytics 4, which will soon completely replace it, and the most notable differences. Happy reading.A Brief Historical Overview of Google Analytics Urchin was the most popular tool for monitoring website traffic in the early 2000s. Google couldn't remain passive in the face of this popularity and made the move that would directly affect our present by acquiring Urchin Software Corp. in 2005. The naming, which was initially “Urchin from Google”, was later named “Google Analytics”, which we still use today, and it has evolved a lot since Google first acquired it in 2005. Over the years, as the internet became widespread and people's shopping habits evolved, Analytics has become one of the most important tools for us to keep user data online and make sense of it. 2005 → GA1: Google Analytics (urchin.js) 2008 → GA2: Google Analytics Classic (ga.js) 2012 → GA3: Google Analytics Universal (analytics.js) 2020 → GA4: Google Analytics 4 In our upcoming headings, we will first examine Google Analytics 4, which was announced as APP+Web.When is Universal Analytics Being Phased Out? What to Pay Attention to? Google has postponed the shutdown of UA several times, but we are getting closer to the inevitable end every day. Although GA4 has not yet exited the beta phase, it has been announced that Google will stop collecting data after July 2023 and will not allow new processing. You can find the latest announcement here. Important point: You need to export your data within 6 months, because Google does not guarantee access to this data. 360 Universal Analytics properties are granted an additional year of use, until July 1, 2024.Key Points * UA shuts down on July 1, 2023. * The shutdown date for 360 properties is July 1, 2024. * Data will be accessible for 6 months. * Exporting your data is very important to avoid data loss.What Does GA4 Offer Us? What Does It Aim For? Google Analytics 4 (GA4) is the latest version of Google Analytics. It is largely different from the old Universal Analytics (GA3) platform in terms of its features and data collection method. GA4 prioritizes user privacy when collecting data and performs tracking based on events, not sessions.With these changes, Google is adding AI-powered analysis to its reporting systems. Although it does not yet provide the desired accuracy, we think that AI-supported reporting will be used frequently in Analytics in the future. In addition, GA4 has opened a new window on user privacy with many innovations related to cookies and GDPR. In short, GA4 aims to better protect user privacy by offering less personal data collection, more data control, and a shorter data retention period.How Do UA and GA4 Measure Users? The most fundamental difference between UA and GA4 is in their measurement model. Universal Analytics tracks users based on sessions, while GA4 tracks users based on events. Universal Analytics uses a model that focuses on sessions and pageviews. GA4, on the other hand, implements an event-based model. While sessions connect specific user interactions, event data is anonymous and focuses on "what was done." In web analytics, an event is an interaction performed by the visitor on the site or application: click, pageview, scroll, file download, purchase, etc. GA4 evaluates all these interactions as events. In Universal Analytics, special setup with GTM was required to measure such interactions; GA4, on the other hand, offers some automatic tracking features. Still, the popularity of GTM continues.What Are the Changed Metrics from UA to GA4? One of the critical differences between UA and GA4 is how metrics are calculated. For example, metrics like Total Users or Bounce Rate, although they exist on both platforms, give different results. You can see the UA and GA4 metric comparison in the table below.MetricUAGA4Total UsersThe most basic user metricActive UsersNew UsersPeople visiting the site for the first timefirst_open (web), first_visit (app)Active UsersN/APrimary user metricUnique PageviewsUnique pageviewsN/ABounce RateSessions ending without an eventSessions shorter than 10 seconds and with a single eventSource: Google HelpThere may be inconsistencies in UA-GA4 comparisons as GA4 does not yet fully support filters.View and Data Streams The concept of View, which was indispensable in Universal Analytics, does not exist in GA4. In GA4, a website or application is configured as a “Data Stream”, and each property can contain a maximum of 50 streams.Cross-Device Tracking GA4 tracks and reports user behavior across devices thanks to multiple data streams added to the same property. Device-level data (browser, device) and user-level data are combined to provide multi-faceted analysis.Enhanced E-commerce Events For e-commerce sites, the Enhanced E-commerce events of UA and GA4 events are used with different names. You can see their counterparts below:EventUAGA4Product Impressionsimpressionsview_item_listProduct ClicksproductClickselect_itemAdd to CartaddToCartadd_to_cartRemove from CartremoveFromCartremove_from_cartCheckoutcheckoutbegin_checkoutPurchasepurchasepurchaseProduct Detail ViewsproductDetailview_itemPromotion ImpressionspromoViewview_promotionPromotion ClickspromoClickselect_promotionData Collection and Privacy DifferencesData Collection While UA relies on cookies, GA4 can track across devices with an event-based model even if cookies are disabled. UA primarily collects web data, while GA4 collects both web and application data.Privacy GA4 allows you to choose which data to collect and behaves according to user permissions with "Consent Mode". If consent is denied, modeling is done with machine learning. Data is deleted after 14 months; in UA, the period is unlimited.Cookie Policy GA4 abandons third-party cookies and focuses on first-party cookies. Google will change the way data is collected by removing third-party cookies from Analytics and Chrome. We will detail this topic in our next article.

Feb 10, 2023 914 reads

UX Laws and UX Analysis in Light of Neuroscience - AnalyticaHouse

Your brand and its website being discovered, and measuring your users’ thoughts and emotional responses on the path to conversion, is vital for analyzing your customers’ journey.Whenever your users interact with your brand’s website—regardless of platform (app or web)—the sum of their experiences is called user experience, or UX. Many factors influence user experience. In this article, we’ll show you how to identify those factors through UX laws designed with neuroscience in mind, and how to conduct a UX analysis to derive actionable insights.What Is Neuroscience?Neuroscience is an interdisciplinary field that studies the nervous system. It aims to expand our understanding of the brain and nervous system.By combining physiology, anatomy, mathematics, developmental biology, and psychology, neuroscientists work to explain learning, memory, behavior, perception, and consciousness. Researchers in this field study brain functions, neuronal behavior, and how neurological foundations underlie various diseases.As the most complex organ in our body, the brain regulates everything that keeps us alive—from emotions, thoughts, and memory to breathing, touch, motor functions, vision, and hunger. Neuroscience techniques have evolved from molecular and cellular studies of neurons to imaging sensory, motor, and cognitive functions in the brain.UX Laws Through the Lens of NeuroscienceCognitive and psychological factors most strongly shape user experience. UX laws describe general principles for designing and using interactive systems like websites and mobile apps.Designs must anticipate how users perceive their surroundings, empathize with them, and guide them swiftly toward their goals. In short, UX design grounded in neuroscience is essential. If a design hasn’t followed these principles, analysts should use neuroscience-based UX laws to assess and improve the site to align with best practices.Every user interacting with your site is subject to basic psychological principles. A user-centric design that delivers great experiences requires understanding human psychology and applying established laws—developed not only by UX experts like Don Norman and Jakob Nielsen but also by psychologists like Bluma Zeigarnik, who studied human behavior extensively.Neuroscience-Based UX LawsTo enhance user experience and make your site more pleasant and efficient, apply these neuroscience-informed UX laws when conducting your analysis:Aesthetic-Usability EffectUsers often perceive visually appealing designs as more usable. Attractive aesthetics trigger positive brain responses, making users believe the design works better. As a result, aesthetic designs mask usability issues by making users more tolerant of minor flaws.Jakob’s Law"Users expect your site or product to follow familiar interaction patterns."Jakob Nielsen’s principle emphasizes leveraging users’ existing mental models rather than reinventing the wheel. Meeting established expectations ensures a smoother experience. For example, e-commerce sites use a shopping cart icon—deviating from such conventions hurts UX.Hick’s LawThe time to make a decision increases with the number and complexity of choices.Hick and Hyman found that decision time grows logarithmically with the number of options. To reduce cognitive load, limit choices, break complex tasks into smaller steps, highlight recommended options, and introduce features gradually for new users.For instance, Ipekyol’s product listing shows 2–4 items at a time to make decisions easier:Miller’s LawOur working memory can hold only about 7 (±2) items at once.If overwhelmed, the brain struggles. Grouping information into chunks eases processing. Netflix’s menu uses clear category headings, aligning with Miller’s Law:Gestalt PrinciplesHumans will interpret complex visuals in the simplest way possible with minimal cognitive effort.Gestalt laws explain how we group elements by similarity, proximity, continuity, and closure. Visually link related items with color, lines, or frames, but avoid over-cluttering, which can be mistaken for ads.Von Restorff EffectDistinctive items stand out and are more memorable.To highlight critical information or actions, use isolation carefully—don’t overuse contrast, and combine color with motion to ensure accessibility.Peak-End RulePeople judge experiences largely by how they felt at the highest point and at the end.Kahneman et al.’s classic study shows that adding a more pleasant ending makes people prefer longer, not shorter, experiences. In UX, focus on peak moments and the final interaction to leave a positive lasting impression.Zeigarnik EffectUnfinished tasks are better remembered than completed ones.To motivate users, show clear progress indicators. For example, Duolingo’s onboarding uses a progress bar to leverage the Zeigarnik Effect:By applying these neuroscience-based laws, you can design experiences that are both enjoyable and conversion-friendly. As Jakob Nielsen said, you don’t need to reinvent the wheel—just refine it.

Jan 5, 2023 1402 reads

Next Generation Behavioral Analysis Tool: Microsoft Clarity

To analyze the users visiting your site and make your current site compatible with user experience (UX), you need next-generation behavioral analytics tools.At this point, Microsoft Clarity comes into play as a next-generation behavioral analytics tool. If you haven’t heard of Microsoft Clarity before, don’t worry. In this article, we will answer the question “What is Microsoft Clarity?” in detail and share the nuances of how you can use Clarity to perform analyses and make your site UX-compliant.What Is Microsoft Clarity?Microsoft Clarity is a free behavioral analytics tool launched by Microsoft in 2020 that transforms user data into visual insights and shows which parts of your website receive the most interaction. It offers features such as dashboards, heatmaps, session recordings, rage clicks, and dead clicks to help you easily analyze issues that frustrate users.Microsoft Clarity tracks users’ movements on your website to measure and analyze site performance. By measuring every user interaction, it guides you to improve your site’s quality and eliminate errors.In addition to being free, Microsoft Clarity has no traffic limits and is optimized not to slow down your site, making it more advantageous and preferable compared to other behavioral analytics tools.Thanks to its lack of traffic limits, even sites with very high traffic (e.g., 1 million daily visits) can easily use Clarity. Because it is optimized not to slow down page load times, it has less impact on page performance than other tools, ensuring that users don’t have to wait and thus positively impacting user experience. With its intuitive interface, detailed filtering options, heatmaps, and session recordings, you can perform a detailed UX analysis of your site; detect dead clicks, rage clicks, and JavaScript errors on your platforms, and improve the current situation.What Are the Features of Microsoft Clarity?The most critical and important feature of Microsoft Clarity for brand and UX analysts is its control panel.In addition to the control panel, with Clarity you can see which page visits users have made on your site (via the Recordings section) and exactly where each visitor clicked (via the Heatmaps section), and from that you can refine your UX analyses.If we look at each page, first let’s see what greets us on the Dashboard:DashboardAs you can see in the image below, once you create your site project in the tool and complete the necessary setup, a dashboard appears where you can easily view all detailed parameters. The control panel provides a general overview of your site visitors’ performance and behavior, allowing you to analyze site traffic in detail and perform aggregate measurements. You can track users’ page movements and view any errors they encountered during their session in detail.In summary, the control panel provides a series of website metrics, which can be described as follows: Sessions: The number of sessions users have on your website, shown as Total Sessions on the dashboard. Pages per Session: The average number of pages per session that users view on your site. Scroll Depth: The percentage of the page that users scroll down on your site. Time Spent: Displays how long users spend on your site actively and inactively. While metrics like Sessions and Scroll Depth inform us about session counts and durations, the metrics below use click data to reveal errors users encounter and the clicks that caused them: Dead Clicks: When users click on an element on your site but get no response. Dead clicks often indicate broken links or JavaScript errors. Rage Clicks: When a user repeatedly clicks in one area, usually due to frustration from dead clicks. Rage clicks can point to insufficient target sizes or misleading visual design. Excessive Scrolling: When a user scrolls up and down a page more frequently than average. Excessive scrolling can indicate poor discoverability or irrelevant content. Quick Backs: When users quickly return to the previous page after navigating to a page. High quick-back rates may indicate misleading or inaccurate content descriptions. You can also analyze which locations and devices users come from and which pages or products they view most often on your site: Most Viewed Products: On an e-commerce site, shows which product receives the most views. Popular Pages: Displays the most visited pages on your site. Referrers: Shows which external pages users came from to visit your site. Browsers: Displays which browsers users use to access your site, helping segment the audience more meaningfully. Devices: Shows which devices users use to visit your site, aiding audience analysis. Countries: Displays the countries from which users visit your site, allowing you to tailor site design to your audience. The filter at the top of the control panel lets you customize analyses by page, date, or device, making Clarity an exceptional experience for UX analysis.RecordingsThe Recordings page lets you watch recordings of user sessions on your site. Using the Recording section, you can replay each visitor’s page visits and see exactly where they clicked, what they scrolled, paused on, and which other pages they navigated to. By applying filters for dead clicks, rage clicks, or JavaScript errors, you can focus on those sessions and create an action plan to minimize these issues.The Recordings page displays user sessions as a timeline and allows you to play back each session like a video, making Clarity a must-have next-gen behavioral analytics tool for UX analysts. In addition to tracking cursor movements and clicks, recordings also provide details like entry and exit URLs, session duration, date, and device. The “Skip Inactive” button helps you save time by skipping long idle periods when reviewing multiple sessions.Recordings also reveal how long users waited during a session and give insights into page load times, which can inform your SEO efforts. The “More Details” option on each video presents a timeline of user actions, giving you deeper insights into both sessions and users.HeatmapsMicrosoft Clarity’s heatmaps help you easily understand how users interact with a page by visualizing sessions with color gradients from red to blue. Warmer colors (reds) show areas with high click density, while cooler colors (blues) indicate areas with low interaction.This feature lets you see exactly where users clicked and how far they scrolled, offering clues about why and how they reached specific areas. Clarity provides three types of heatmaps for in-depth UX analysis: Click Heatmaps: Shows clicks by desktop, mobile, or tablet users on your site. Scroll Heatmaps: Displays the percentage of the page viewed by users as they scroll down. Area Heatmaps: Indicates regional clicks by desktop, mobile, or tablet users on your site. By filtering click and area click data for specific date ranges, you can identify which areas of your site’s homepage were most engaging. For example, during Black Friday, you might find that users clicked most on “Women > Jeans.” Further analysis may reveal that mobile users most often clicked “Mom Jeans,” size 32/33, in Dark Blue, but encountered dead clicks on the size filter, preventing them from reaching the cart. This indicates a need for quick fixes in that area to improve conversion.Additionally, for future campaigns, you could use remarketing to target mobile users interested in “Mom Jeans,” size 32/33, Dark Blue, thereby improving conversion rates. From these examples and Clarity’s versatile panels, it’s clear that Microsoft Clarity is arguably the best next-gen behavioral analytics tool for UX analysis on your sites.We hope this article encourages you to integrate Microsoft Clarity more into your UX analyses.See you in our next article...

Oct 21, 2022 2874 reads

Market Basket Analysis

In today’s world, after the very well known pandemic we had through, the e-commerce sector rose like the sun. With this raise, websites of almost every brand from relatively small businesses to the largest businesses have gained a lot more popularity and their traffic has increased almost 50%. According to the International Trade Administration (2021), an average of 19% increase in e-commerce revenue is forecasted (26% in Food & Personal Care products) after the pandemic.These growth statistics and developments tell us one significant thing that the businesses should start to give more attention (and more budget) to their e-commerce/marketing departments and their operations. When e-commerce is mentioned, the first thing that comes to mind is obviously websites. Products are being tried to be exhibited in websites in such ways that help business owners to sell more products and gain more revenue from their most valuable resources which are customers. There are tens of ways to take the attention of customers and give them the intent of simply buying more. In this article, I will try to explain a method called “Basket Analysis”.What is Basket Analysis?Basket Analysis is a method that research and study on the baskets (carts) of customers in the website and analyse them to offer meaningful and customised product suggestions to the customers. Before getting through to the technical part of the analysis, there are some more things that we should better mention. Every customer is different as well as their purchase behaviour. Every product is different. However, some of them are used and bought together. In some situations, very unrelated products are sold together and human eyes sometimes cannot determine these ones. Exactly here, artificial intelligence and machine learning enter the stage.Let’s dive deeper into algorithms.Apriori AlgorithmThe Apriori algorithm has been in our minds since 1994 and it helps us find frequent item sets in a dataset for boolean association rules. Name of the algorithm is Apriori because it uses prior knowledge of frequent item set properties.In this algorithm, as mentioned above, the dataset must include products that are frequently bought. The data we need to apply this algorithm includes the following columns: Transaction ID (Basket ID) Product SKU (Product ID) Product Category Quantity After we obtain the necessary data, the magic starts.This algorithm can be written and applied by R Studio, Python etc.Since our data is breakdowned and thus has duplicate transaction ID’s, first we need to group the data by transaction ID and learn every distinct product that has been sold (obviously added to basket before the payment step) in that specific transaction.After this is done, we get dummy variables of all products and create new columns for each of them. For every unique transaction row, the quantity of the product is written to the cell of its own column and transaction. A sample processed data can be seen below:Transaction IDProduct AProduct BProduct CProduct D123abc7300456def2011Machine learning has its own rules, obviously. In order to analyse this data and have meaningful insights, we need to encode the cells into 1-0 to determine which product is added to the basket and bought in that specific transaction. The reason to do this is that Apriori Algorithms takes only 1 and 0 values to determine the association between products without any bias such as unrelated quantities. Consider that we are only interested in products that are being sold together.Finally, before we apply the model, we yield the below data:Transaction IDProduct AProduct BProduct CProduct D123abc1100456def1011We use the “frequent_patterns“ tool from “mlxtend” library and import “apriori” and “association_rules” packages to apply the model in an optimised and fast way.After the necessary parameters are adjusted in the model according to the specific dataset and specific purpose, we get the results as a table below:AntecedentsConsequentsAntecedentSupportConsequentSupportSupportConfidenceLiftLeverageConvictionProduct AProduct B0.40.60.50.832.780.0221.67Product AProduct C0.40.30.450.652.110.11.12Product BProduct D0.60.50.50.621.98-0.321.43Note: Values are randomly generated due to privacy issues.Results:OK. But What do they Mean?Here, the most important metrics that we should consider are “support” and“confidence” values. However, you can read the explanations below for a better understanding. Antecedent Support: The rate of the presence of antecedent products over all. Consequent Support: The rate of the presence of consequent products over all. Support: The rate of presence of antecedent product and consequent product being together in basket over all. Confidence: The confidence rate of products’ being together in the same basket. Lift: Confidence over expected confidence. Leverage: The statistical independency rate of a specific basket according to including products in it. Conviction: Gets higher when the consequent product is highly dependent on the antecedent product. After we yield the result table, we can start to analyse the results. How we do this analysis is according to some statistical methods. We should determine a threshold value for the “confidence” metric and split the rows into two parts: Meaningful or Not.When the confidence value is more than the threshold value, say 0.6, we can conclude that this relationship between products is meaningful and customers frequently buy these products together. Where to Use these Results? Where to use these results is another challenge.Businesses usually use this information for suggestion algorithms and shelf design. For instance, Product B is suggested to the customer who has just added Product A to his/her basket because the confidence level of these products is higher than our threshold value. Thus, the possibility of customer’s missing, forgetting or just not being interested in Product B is decreased and thus, we are being able to direct the customer to buy Product A. Secondly, shelf design (product listing pages in our case) can be conducted and applied to our website according to the results. For instance, Product A and Product B are located near each other to remind customers that they can buy them together (because they generally do it, don’t they?!).Thirdly, campaign scenarios can be set up for customers. For instance, Product B is presented with discounted prices for those customers who add Product A to their baskets or simply buy them before. Last but not least, the results of this analysis can help the business owners and marketers to design their offline (physical) stores’ shelves. Just like the product listing pages in websites, stores shelves can also be designed in such a way that customers can see related and frequently bought products together. In these ways, sale amount, order amount, revenue, traffic that website gains and key performance indicators like these may be increased. Besides, product & marketing costs can be allocated according to the results.

Oct 21, 2022 4436 reads

Product Scoring Algorithm

You are curious about performance of your products. And also, you are worried about how you can manage your product scope to increase revenue. Here are the answers for all of your questions, check out our blog and learn about our product scoring algorithm.Common problems in product managementThere are a number of questions that professionals might have in their mind while evaluating their companies’ performance. And some of these questions are more beneficial when thinking about important actions to increase efficiency of products that are sold on websites, apps and marketing channels.Here are some “general” questions that each team might be curious about the answers to. Which e-commerce metrics should we focus on while considering inventory management? Which products are more valuable? How can we increase our revenue by having the same product scope? What should be our key metrics for optimising marketing campaigns of our products? How should we decide our product listing in our website or app? Yes, you are right! AnalyticaHouse Data Science & Insights Team have another magical algorithm that would be helpful for all mysterious questions above and more, which is Product Scoring Algorithm. In this article, we will be talking about the structure of this algorithm and applications of it in the digital marketing sector.How is the algorithm built?There are a lot of variants for product groups in each website and app differentiating based on various dimensions such as colours, sizes, product types, season/offseason, target genders, target age groups and so on. We would be able to analyse every detail of products and product variants thanks to the Product Scoring Algorithm depending on the depth of the data we have.The minimum data requirement for this analysis are transactional data of products and current inventory information of them. We are focusing on these metrics while analysing transactional data; number of purchases, total quantity, revenue, average price and so on. Of course, this analysis would be more interesting when we have user/session-based data. We would be able to add other important metrics such as product detail views, add to cart, # of buyers, # of users who look at the product, revenue/product detail views, transaction/product detail views and so on. These metrics can be grouped into parts according to results they show; Revenue supporting metrics : number of purchases, total quantity, revenue, average price, revenue/product detail views, transaction/product detail viewsMetrics that show customer interest : product detail views, add to cart, # of buyers, # of users who look at the product, revenue/product detail viewsMetric definitions number of purchases: Number of transactions Total quantity:  Number of products that are purchased Revenue: Total amount of revenue Average Price: Average price of products revenue/product detail views: Revenue per product detail views for each product transaction/product detail views: Conversion rate (based on product detail views) add to cart: Total number of products that are added to cart # of buyers: Total number of customers who purchased related product # of users who look at the product: Total number of users who viewed related product Application of the modelThe algorithm can be applied to each product level and can bring insights for bigger picture and tiny details.The example below shows a category/product level for an e-commerce company; Level 1: Shoes/Bags Level 2: Shoes Level 3: Sneakers Level 4: X Brand’s Sneakers Level 5: X Brand’s White Sneakers Level 6: X Brand’s White Sneakers with Size:38 How is product score calculated?Product Scoring Algorithm is basically formed from two parts. The first part is based on calculating ratio of lower levels (eg. X Brand’s White Sneakers with Size:38) in totals of higher levels (eg. X Brand’s Sneakers) by using metrics that we discussed above, and we will explain this part by showing an example. The second part is dependent on current inventory information of products, and this part is very crucial when we take inventory management into account for short term and long term.  Example above shows a product scoring calculation by using metrics add to cart and quantity sold in addition to instant inventory score ( if there is inventory it is 1 and if not it is 0). In this example distribution of level 6 in total of level 5 for add to cart and quantity sold metrics and inventory score are used as three multipliers of product score of level 6.  After calculating the score of each row (each breakdown, for this example it is level 6), we calculate the score of the higher level ( in this example it is level 5 ). We take the sum of the score of all breakdowns for level 5 and as a result we have the total score of level 5. For example; for X brand’s White Sneakers the total score can be calculated as :0,0747 + 0,0245 + 0,0036 + 0,0028 + 0,0251 + 0,0000 = 0,131In this example X brand’s Black Sneakers has the highest score (0,193) and X brand’s Red Sneakers has the smallest score (0,071).How can we use the results?This analysis can be applied to all levels from bottom to top. And of course, this analysis can be enlarged with additional metrics that we talked about before and results can be calculated in more detail. In addition to that, we can change the importance of each metric in the calculation step of the product score by using Variable Importance Analysis which is another outstanding algorithm that our team improved. Last but not least, results of the analysis can be used for updating product feed automatically for marketing campaigns.