Demographics-based, product discovery
Prereq.: Research papers: foundation of industry-academic...
May be related:
Synergizing demographics and purchase history
Product recommender systems are often deployed by e-commerce websites to improve user experience and increase sales. However, recommendation is limited by product information hosted in those e-commerce sites and is only triggered when users are performing e-commerce activities. Microblogs alternatively contain public profiles of users, including age, sex and/or professions from which [1] detects users’ purchase intents in near real-time. Product demographics, also called target audience, is a collection of characteristics of people who buy the product. Similarity measurement is performed between a user and products based on features derived from their demographic information. Product recommendations - framed as a learning-to-rank problem, are based on matching users’ demographic information extracted from their public profiles with product demographics learned from microblogs and online reviews.
Availability of purchase data from multiple commercial e-mail domains puts an e-mail provider in the unique position to be able to build better recommendation systems (Customers who bought X from vendor V1 also bought Y from vendor V2) than those based on any one commercial e-mail domain alone (e.g.,Customers who bought X also bought Y)”. [2] leverages e-mail receipts to embed products into real-valued, low-dimensional vector space using a neural language model applied to a time series of user purchases. Products with similar contexts (i.e., their surrounding purchases) are mapped to vectors that are nearby in the embedding space. For next basket prediction, product vectors are clustered further and transition probabilities between clusters are modelled. The closest products in the embedding space from the most probable clusters are used to form final recommendations. Approach valuation was against baselines showing popular products and products predicted based on co-occurrence.
For online product recommendation engines, learning high-quality product embedding that captures various aspects of the product is critical to improving the accuracy of user rating prediction. In recent research, in conjunction with user feedback, the appearance of a product as side information has been shown to be helpful for learning product embedding. However, since a product has a variety of aspects such as functionality and specifications, taking into account only its appearance as side information does not suffice to accurately learn its embedding. [4] propose a matrix co-factorization method that leverages information hidden in the so-called “also-viewed” products, i.e., a list that has also been viewed by users who have viewed a target product. “Also-viewed” products reflect various aspects of a given product that have been overlooked by past, visually-aware recommendation methods.
[4] addresses the following questions: (1) what are the intents of users underlying their search activities? (2) do users behave differently under different search intents? and (3) how does user perceived satisfaction relate to their search behaviour as well as search intents, and can we predict product search satisfaction with interaction signals? Based on an online survey and search logs collected from a major commercial product search engine, user intents in product search engines are shown to fall into three categories: Target Finding (TF), Decision Making (DM) and Exploration (EP). Through a log analysis and a user study, different user interaction patterns as well as perceived satisfaction under these three intents are observed. Using a series of user interaction features, it is demonstrated that user satisfaction, especially for TF and DM intents, can be effectively predicted.
- We Know What You Want to Buy: A Demographic-based System for Product Recommendation On Microblogs
- E-commerce in Your Inbox: Product Recommendations at Scale
- Do “Also-Viewed” Products Help User Rating Prediction?