Machine Learning in E‑commerce
summary
Covers building and operating large-scale predictive analytics for an e-commerce/CRM product (Bitrix24): designing, training and tuning Spark MLlib models in AWS Spark clusters to predict paying customers, customer lifetime value and churn. Describes algorithm and library selection, big-data filtering and processing on Spark, and engineering practices needed to deploy these predictive models into a high-load production service.
AI-written summary · about
chapters (21)
- 0:00Introduction
- 1:06Machine learning in business
- 3:54Science vs programming
- 6:01Neural networks revolution
- 9:31How neural networks work
- 12:00ML in e-commerce
- 18:23Data collection and processing
- 24:20Data analysis and visualization
- 26:49Customer cluster analysis
- 27:53Recommendation personalization
- 32:13Business classification
- 34:17AI customer support
- 37:27Regression and forecasting
- 38:29Chatbots and AI
- 41:37Bot platforms
- 43:02Semantic search
- 45:10Behavior cause analysis
- 46:32AI strategy
- 47:35Marketing problems
- 48:38Neural networks future
- 51:08Breakthrough research
related talks
56mMachine Learning in E‑commerce
37mForecasting using machine learning methods
22mReal-world applications of machine learning: Beyond the hype
27mUnlocking Product Growth With Big Data, Data Science And Machine Learning
23mCustom-made games with machine learning and big data
48mMachine Learning in Azure Databricks
47mBuilding ML practices to address the top four use cases
44mApache Spark and ML workflows