Tata Consultancy Services Limited

Priyanka Gupta

Gautam Shroff

Lovekesh Vig

Pankaj Malhotra

Diksha Garg

Ankit Sharma

Recommender Systems (RS) tend to recommend more popular items instead of the relevant long-tail items. Mitigating such popularity bias is crucial to ensure that less popular but relevant items are recommended. System described herein analyses popularity bias in session-based RS obtained via deep learning (DL) models. DL models trained on historical user-item interactions in session logs (having long-tailed item-click distributions) tend to amplify popularity bias. To understand source of this bias amplification, potential sources of bias at data-generation stage (user-item interactions captured as session logs) and model training stage are considered by the system for recommendation wherein popularity of item has causal effect on user-item interactions via conformity bias, and item ranking from models via biased training process due to class imbalance. While most existing approaches address only one of these effects, a comprehensive causal inference framework is implemented by present disclosure that identifies and mitigates effects at both stages.

System, method, and non-transitory machine-readable information storage medium for recommendations of items and controlling an associated bias thereof

Session-based Recommendation (SR) is the task of recommending the next item based on previously recorded user interactions. However, most existing approaches for SR either rely on costly online interactions with real users (model-free approaches) or rely on potentially biased rule-based or data-driven user-behavior models (model-based approaches) for learning. This disclosure relates to a system and method for selecting session-based recommendation policies using historical recommendations and user feedback. Herein, the learning of recommendation policies given offline or batch data from old recommendation policies based on a Distributional Reinforcement Learning (DRL) based recommender system in the offline or batch-constrained setting without requiring access to a user-behavior model or real-interactions with the users.

System and method for training recommendation policies

This disclosure relates generally to method and system for handling popularity bias in item recommendations. In an embodiment the method includes initializing an item embedding look-up matrix corresponding to items in a sequence of item-clicks with respect to a training data. L2 norm is applied to the item embedding look-up matrix to learn a normalized item embeddings. Using a neural network, a session embeddings corresponding to the sequences of item-clicks is modeled and L2 norm is applied to the session embeddings to obtain a normalized session embeddings. Relevance scores corresponding to each of the plurality of items are obtained based on similarity between the normalized item embeddings and the normalized session embeddings. A multi-dimensional probability vector corresponding to the relevance scores for the items to be clicked in the sequence is obtained. A list of the items ordered based on the multi-dimensional probability vector is provided as recommendation.

System, method, and non-transitory machine readable information storage medium for handling popularity bias in item recommendations

Traditional systems and methods have implemented hand-crafted feature extraction from varying length time series that results in complexity and requires domain knowledge. Building classification models requires large labeled data and is computationally expensive. Embodiments of the present disclosure implement learning models for classification tasks in multi-dimensional time series by performing feature extraction from entity's parameters via unsupervised encoder and build a non-temporal linear classifier model. A fixed-dimensional feature vector is outputted using a pre-trained unsupervised encoder, which acts as off-the shelf feature extractor. Extracted features are concatenated to learn a non-temporal linear classification model and weight is assigned to each extracted feature during learning which helps to determine relevant parameters for each class. Mapping from parameters to target class is considered while constraining the linear model to use only subset of large number of features.

Growing community of inventors

Noida, India

Priyanka Gupta