Lesson 1Design of transactional tables: orders, order_items, returns, lifetime_value signals and field choicesLearn to create main transactional tables that record orders, items, returns, and lifetime value hints. We talk about vital fields, standardisation options, and supporting later analysis and recommendation tasks in local e-commerce systems.
Order header vs line item schema designModeling returns, refunds, and cancellationsCapturing discounts, coupons, and taxesStoring lifetime value and margin signalsKeys, indexes, and partitioning choicesLesson 2Handling noisy and sparse behavioral data: sessionization, bot filtering, deduplication, event weightingLook into ways to tidy messy behaviour records and use thin data effectively. You will learn session rules, bot and scraper removal, duplicate removal steps, and event importance tactics fitted for recommendation training in Zimbabwean contexts.
Sessionization rules and timeoutsDetecting and filtering bots and scrapersClick, view, and purchase deduplicationEvent weighting for model trainingHandling sparse users and cold startsLesson 3Design of product catalog table: product_id, title, category hierarchy, attributes, price, brand, stock, images, canonical_text, embeddingsLearn to organise a product catalog table for quick access and detailed recommendations. We cover IDs, features, prices, stock, media, standard text, and embeddings, plus plans for updates and non-standardisation in e-commerce.
Stable product and variant identifiersCategory hierarchy and attributesPrice, stock, and availability fieldsImages, media, and canonical textStoring and updating item embeddingsLesson 4Feature engineering principles for recommendations: recency, frequency, monetary, item popularity, category affinity, user embeddingsFind out main feature creation rules for recommender systems. We explain recency, frequency, money value, popularity, category links, and user embeddings, including grouping periods and safe calculation methods without leaks.
Recency, frequency, and monetary featuresItem and category popularity signalsUser–category and brand affinity scoresSequence‑based and session featuresUser and item embedding generationLesson 5Auxiliary datasets: item metadata, taxonomy, promotions, content (descriptions), supplier dataUnderstand how extra datasets improve recommendations past basic clicks and orders. We cover item details, category systems, deals, content, and supplier inputs, plus keeping them steady, versioned, and connectable at large scales in Zimbabwe.
Designing item metadata schemasMaintaining product taxonomy hierarchiesModeling promotions and price rulesStoring rich content and descriptionsIntegrating supplier and feed dataLesson 6Data cleaning and imputation strategies: missing attributes, price anomalies, invalid timestampsLearn useful data cleaning and filling methods for e‑commerce. We tackle missing features, odd prices, wrong times, and uneven currencies, stressing rules, shortcuts, and effects on recommendation standards in local settings.
Detecting and fixing missing attributesHandling outlier and zero pricesCorrecting invalid or noisy timestampsCurrency, tax, and unit normalizationDocumenting cleaning rules and impactsLesson 7Design of event stream and interaction table: event_id, user_id/session_id, event_type, product_id, timestamp, context (referrer, page_type), device, event_valueCreate a single interaction table and event flow that records user actions across platforms. Learn event designs, IDs, context fields, and supporting live streaming and batch recommendation processes in e-commerce.
Choosing event and user identifiersModeling event types and propertiesCapturing context, device, and referrerEvent time, ingestion time, and orderingStreaming vs batch storage patternsLesson 8Design of user profiles table: essential fields (user_id, signup_ts, email_hash, demographics, lifecycle stage, segments, opt‑in flags) and rationaleCreate a user profiles table that weighs personalization strength against privacy and rules. We cover key fields, life stages and groups, opt-in markers, hashing private data, and how profiles supply recommendation models.
Core identifiers and signup metadataDemographics and lifecycle stagesBehavioral and marketing segmentsConsent, opt‑in, and preference flagsPrivacy, hashing, and retention rules
