Lesson 1Structuring of transaction tables: orders, order items, returns, lifetime value signs and field optionsLearn to structure main transaction tables that record orders, line items, returns, and lifetime value signs. We talk about key fields, standardisation choices, and how to aid later analysis and recommendation tasks.
Order header vs line item schema designModeling returns, refunds, and cancellationsCapturing discounts, coupons, and taxesStoring lifetime value and margin signalsKeys, indexes, and partitioning choicesLesson 2Dealing with messy and thin behaviour data: session grouping, bot removal, duplicate removal, event weightingLook into ways to clean messy behaviour records and make thin data useful. You will learn session grouping rules, bot and scraper removal, duplicate logic, and event weighting plans suited to recommendation training.
Sessionization rules and timeoutsDetecting and filtering bots and scrapersClick, view, and purchase deduplicationEvent weighting for model trainingHandling sparse users and cold startsLesson 3Structuring of product stock table: product_id, title, category tree, features, price, brand, stock, images, standard text, embeddingsLearn to organise a product stock table that aids quick fetching and rich recommendations. We cover identifiers, features, pricing, stock, media, standard text, and embeddings, plus plans for updates and non-standardisation.
Stable product and variant identifiersCategory hierarchy and attributesPrice, stock, and availability fieldsImages, media, and canonical textStoring and updating item embeddingsLesson 4Feature creation basics for recommendations: newness, frequency, monetary, item popularity, category liking, user embeddingsFind core feature creation basics for recommender systems. We explain newness, frequency, monetary value, popularity, category liking, and user embeddings, including grouping windows and leak-proof calculation patterns.
Recency, frequency, and monetary featuresItem and category popularity signalsUser–category and brand affinity scoresSequence‑based and session featuresUser and item embedding generationLesson 5Support datasets: item details, category system, deals, content (descriptions), supplier dataUnderstand how support datasets improve recommendations beyond basic clicks and orders. We cover item details, category system, deals, content, and supplier inputs, plus how to keep them steady, versioned, and linkable at large scale.
Designing item metadata schemasMaintaining product taxonomy hierarchiesModeling promotions and price rulesStoring rich content and descriptionsIntegrating supplier and feed dataLesson 6Data cleaning and filling strategies: missing features, price oddities, wrong timestampsLearn useful data cleaning and filling methods for e-commerce. We handle missing features, odd prices, wrong timestamps, and uneven currencies, focusing on rules, shortcuts, and effect on recommendation quality.
Detecting and fixing missing attributesHandling outlier and zero pricesCorrecting invalid or noisy timestampsCurrency, tax, and unit normalizationDocumenting cleaning rules and impactsLesson 7Structuring of event flow and interaction table: event_id, user_id/session_id, event_type, product_id, timestamp, context (referrer, page_type), device, event_valueStructure a single interaction table and event flow that records user actions across channels. Learn event designs, identifiers, context fields, and how to aid both live streaming and offline batch recommendation lines.
Choosing event and user identifiersModeling event types and propertiesCapturing context, device, and referrerEvent time, ingestion time, and orderingStreaming vs batch storage patternsLesson 8Structuring of user profiles table: key fields (user_id, signup_ts, email_hash, demographics, life stage, segments, opt-in flags) and reasonsStructure a user profiles table that balances personalisation strength with privacy and rules. We cover key fields, life stages and segments, opt-in flags, hashing sensitive data, and how profiles feed recommendation models.
Core identifiers and signup metadataDemographics and lifecycle stagesBehavioral and marketing segmentsConsent, opt‑in, and preference flagsPrivacy, hashing, and retention rules
