In e-commerce, the watchlist enables users to track items over time and has emerged as a primary feature, playing an important role in users' shopping journey. Watchlist items typically have multiple attributes whose values may change over time (e.g., price, quantity). Since many users accumulate dozens of items on their watchlist, and since shopping intents change over time, recommending the top watchlist items in a given context can be valuable. In this work, we study the watchlist functionality in e-commerce and introduce a novel watchlist recommendation task. Our goal is to prioritize which watchlist items the user should pay attention to next by predicting the next items the user will click. We cast this task as a specialized sequential recommendation task and discuss its characteristics. Our proposed recommendation model, Trans2D, is built on top of the Transformer architecture, where we further suggest a novel extended attention mechanism (Attention2D) that allows to learn complex item-item, attribute-attribute and item-attribute patterns from sequential-data with multiple item attributes. Using a large-scale watchlist dataset from eBay, we evaluate our proposed model, where we demonstrate its superiority compared to multiple state-of-the-art baselines, many of which are adapted for this task.

An online shaping technique for high performance communication over Gaussian channels with Inter-Symbol Interference (ISI) and receiver Analog to Digital Converter (ADC) noise is presented. The technique uses online transmitter precoding over Pulse Amplitude Modulation (PAM) constellation, designed to shape the symbols distribution so that peak power constraint at the channel output is satisfied. An iterative decoder shares information between a modified M-BCJR module, which computes online the trellis transition probabilities of the shaped distribution, and turbo decoder. The result is a reduction in the required Effective Number Of Bits (ENOB) of the receiver ADC. We show that the transmitter precoding performs channel equalization without using any filter. At the limit of very high Signal to Noise Ratio (SNR) a complete channel inversion is possible so that the receiver signal spectrum becomes almost flat. Theoretical bounds are analytically derived which enable to assess the possible gain using the proposed method. For data rates of 200 Gbps and 400 Gbps over printed circuit board, simulations show that the shaping scheme enables reduction in the ENOB requirement as high as 1.43 bit and 1.78 bit, respectively, compared to uniform 4-PAM transmission with turbo equalization at the receiver side.

An online shaping technique for high performance communication over Gaussian channels with Inter-Symbol Interference (ISI) and receiver Analog to Digital Converter (ADC) noise is presented. The technique uses online transmitter pre-coding over Pulse Amplitude Modulation (PAM) constellation, designed to shape the symbols distribution so that peak power constraint at the channel output is satisfied. An iterative decoder shares information between a modified M-BCJR module, which computes online the trellis transition probabilities of the shaped distribution, and turbo decoder. The result is a reduction in the required ADC Effective Number Of Bits (ENOB), which is in particular attractive in modern high-speed wireline links. Theoretical bounds are analytically derived which enable to assess the possible gain using shaping. On practical scenarios aim to transmit 200 Gbps and 400 Gbps over printed circuit board, we demonstrate in simulations an overall ENOB gains as high as 1.43 bit and 1.78 bit, respectively, compared to uniform 4-PAM transmission with turbo equalization at the receiver side.

Recent advances in the e-commerce fashion industry have led to an exploration of novel ways to enhance buyer experience via improved personalization. Predicting a proper size for an item to recommend is an important personalization challenge, and is being studied in this work. Earlier works in this field either focused on modeling explicit buyer fitment feedback or modeling of only a single aspect of the problem (e.g., specific category, brand, etc.). More recent works proposed richer models, either content-based or sequence-based, better accounting for content-based aspects of the problem or better modeling the buyer's online journey. However, both these approaches fail in certain scenarios: either when encountering unseen items (sequence-based models) or when encountering new users (content-based models).

A novel PAPR shaping technique intended for systems with high spectral efficiency and single carrier transmission is presented. This technique applies puncturing of error correction redundancy bits to achieve a desired Markovian symbol transmission probability distribution, which avoids symbol sequences with high peak values. For a 16-QAM system with transmission rate of 3 bit/symbol and a root raised cosine (RRC) pulse shape filter with roll-off factor 0.1 and duration of six symbols, an overall gain of about 2.2 dB is demonstrated by simulations using pragmatic binary turbo code for error correction. The technique can be used to improve any single carrier communication link limited by the high power amplifier (HPA) peak power.

Web search engines present, for some queries, a cluster of results from the same specialized domain (“vertical”) on the search results page (SERP). We introduce a comprehensive analysis of the presentation of such clusters from seven different verticals based on the logs of a commercial Web search engine. This analysis reveals several unique characteristics—such as size, rank, and clicks—of result clusters from community question-and-answer websites. The study of properties of this result cluster—specifically as part of the SERP—has received little attention in previous work. Our analysis also motivates the pursuit of a long-standing challenge in ad hoc retrieval, namely, selective cluster retrieval . In our setting, the specific challenge is to select for presentation the documents most highly ranked either by a cluster-based approach (those in the top-retrieved cluster) or by a document-based approach. We address this classification task by representing queries with features based on those utilized for ranking the clusters, query-performance predictors, and properties of the document-clustering structure. Empirical evaluation performed with TREC data shows that our approach outperforms a recently proposed state-of-the-art cluster-based document-retrieval method as well as state-of-the-art document-retrieval methods that do not account for inter-document similarities.

We address the long standing challenge of selective cluster-based retrieval; namely, deciding on a per-query basis whether to apply cluster-based document retrieval or standard document retrieval. To address this classification task, we propose a few sets of features based on those utilized by the cluster-based ranker, query-performance predictors, and properties of the clustering structure. Empirical evaluation shows that our method outperforms state-of-the-art retrieval approaches, including cluster-based, query expansion, and term proximity methods.