No abstract

No abstract

No abstract

Post-click conversion, as a strong signal indicating the user preference, is salutary for building recommender systems. However, accurately estimating the post-click conversion rate (CVR) is challenging due to the selection bias, i.e., the observed clicked events usually happen on users' preferred items. Currently, most existing methods utilize counterfactual learning to debias recommender systems. Among them, the doubly robust (DR) estimator has achieved competitive performance by combining the error imputation based (EIB) estimator and the inverse propensity score (IPS) estimator in a doubly robust way. However, inaccurate error imputation may result in its higher variance than the IPS estimator. Worse still, existing methods typically use simple model-agnostic methods to estimate the imputation error, which are not sufficient to approximate the dynamically changing model-correlated target (i.e., the gradient direction of the prediction model). To solve these problems, we first derive the bias and variance of the DR estimator. Based on it, a more robust doubly robust (MRDR) estimator has been proposed to further reduce its variance while retaining its double robustness. Moreover, we propose a novel double learning approach for the MRDR estimator, which can convert the error imputation into the general CVR estimation. Besides, we empirically verify that the proposed learning scheme can further eliminate the high variance problem of the imputation learning. To evaluate its effectiveness, extensive experiments are conducted on a semi-synthetic dataset and two real-world datasets. The results demonstrate the superiority of the proposed approach over the state-of-the-art methods. The code is available at https://github.com/guosyjlu/MRDR-DL. CCS CONCEPTS• Information systems → Recommender systems.

No abstract

No abstract

Recommender Systems have been playing essential roles in ecommerce portals. Existing recommendation algorithms usually learn the ranking scores of items by optimizing a single task (e.g., Click-through rate prediction) based on users' historical click sequences, but they generally pay few attention to simultaneously modeling users' multiple types of behaviors or jointly optimize multiple objectives (e.g., both Click-through rate and Conversion rate), which are both vital for e-commerce sites. In this paper, we argue that it is crucial to formulate users' different interests based on multiple types of behaviors and perform multi-task learning for significant improvement in multiple objectives simultaneously. We propose Deep Multifaceted Transformers (DMT), a novel framework that can model users' multiple types of behavior sequences simultaneously with multiple Transformers. It utilizes Multi-gate Mixture-of-Experts to optimize multiple objectives. Besides, it exploits unbiased learning to reduce the selection bias in the training data. Experiments on JD real production dataset demonstrate the effectiveness of DMT, which significantly outperforms state-ofart methods. DMT has been successfully deployed to serve the main traffic in the commercial Recommender System in JD.com. To facilitate future research, we release the codes and datasets at https://github.com/guyulongcs/CIKM2020_DMT.

Abstract:Most recommender systems suggest items similar to a user profile, which results in boring recommendations limited by user preferences indicated in the system. To overcome this problem, recommender systems should suggest serendipitous items, which is a challenging task, as it is unclear what makes items serendipitous to a user and how to measure serendipity. The concept is difficult to investigate, as serendipity includes an emotional dimension and serendipitous encounters are very rare. In this paper, we discuss mentioned challenges, review definitions of serendipity and serendipity-oriented evaluation metrics. The goal of the paper is to guide and inspire future efforts on serendipity in recommender systems.