Chapter 1, Association Rule Mining, builds recommender systems with transaction data. We identify cross-sell and upsell opportunities.
Chapter 2, Fuzzy Logic Induced Content-Based Recommendation, addresses the cold start problem in the recommender system. We handle the ranking problem with multi-similarity metrics using a fuzzy sets approach.
Chapter 3, Collaborative Filtering, introduces different approaches to collaborative filtering for recommender systems.
Chapter 4, Taming Time Series Data Using Deep Neural Networks, introduces MXNet R, a package for deep learning in R. We leverage MXNet to build a deep connected network to predict stock closing prices.
Chapter 5, Twitter Text Sentiment Classification Using Kernel Density Estimates, shows ability to process Twitter data in R. We introduce delta-tfidf, a new metric for sentiment classification. We leverage the kernel density estimate based Naïve Bayes algorithm to classify sentiments.
Chapter 6, Record Linkage - Stochastic and Machine Learning Approaches, covers the problem of master data management and how to solve it in R using the recordLinkage package.
Chapter 7, Streaming Data Clustering Analysis in R, introduces a package stream for handling streaming data in R, and the clustering of streaming data, as well as the online/offline clustering model.
Chapter 8, Analyzing and Understanding Networks Using R, covers the igraph package for performing graph analysis in R. We solve product network analysis problems with graph algorithms.
