Food delivery platforms face the challenge of helping users navigate vast catalogs of restaurants and dishes to find meals they truly enjoy. This paper presents RED, an automated recommendation system designed for iFood, Latin America's largest on-demand food delivery platform, to personalize the selection of curated food collections displayed to millions of users. Our approach employs a LightGBM classifier that scores collections based on three feature groups: collection characteristics, user-collection similarity, and contextual information. To address the cold-start problem of recommending newly created collections, we develop content-based representations using item embeddings and implement monotonicity constraints to improve generalization. We tackle data scarcity by bootstrapping from category carousel interactions and address visibility bias through unbiased sampling of impressions and purchases in production. The system demonstrates significant real-world impact through extensive A/B testing with 5-10% of iFood's user base. Online results of our A/B tests add up to 97% improvement in Card Conversion Rate and 1.4% increase in overall App Conversion Rate compared to popularity-based baselines. Notably, our offline accuracy metrics strongly correlate with online performance, enabling reliable impact prediction before deployment. To our knowledge, this is the first work to detail large-scale recommendation of curated food collections in a dynamic commercial environment.

Sequential recommender systems aim to model users' evolving preferences by capturing patterns in their historical interactions. Recent advances in this area have leveraged deep neural networks and attention mechanisms to effectively represent sequential behaviors and time-sensitive interests. In this work, we propose C-TLSAN (Content-Enhanced Time-Aware Long- and Short-Term Attention Network), an extension of the TLSAN architecture that jointly models long- and short-term user preferences while incorporating semantic content associated with items, such as product descriptions. C-TLSAN enriches the recommendation pipeline by embedding textual content linked to users' historical interactions directly into both long-term and short-term attention layers. This allows the model to learn from both behavioral patterns and rich item content, enhancing user and item representations across temporal dimensions. By fusing sequential signals with textual semantics, our approach improves the expressiveness and personalization capacity of recommendation systems. We conduct extensive experiments on large-scale Amazon datasets, benchmarking C-TLSAN against state-of-the-art baselines, including recent sequential recommenders based on Large Language Models (LLMs), which represent interaction history and predictions in text form. Empirical results demonstrate that C-TLSAN consistently outperforms strong baselines in next-item prediction tasks. Notably, it improves AUC by 1.66%, Recall@10 by 93.99%, and Precision@10 by 94.80% on average over the best-performing baseline (TLSAN) across 10 Amazon product categories. These results highlight the value of integrating content-aware enhancements into temporal modeling frameworks for sequential recommendation. Our code is available at https://github.com/booml247/cTLSAN.

In the context of Meituan Waimai, user behavior exhibits heterogeneous characteristics, including various behavior subjects, content, scenarios. The current industry approach mostly involves continuously adding various heterogeneous behavior to the traditional recommendation models, which brings two obvious problems. Firstly, the multitude of behavior subjects leads to sparse features that pose challenges to efficient modeling. Secondly, separating the modeling of user, merchant, and commodity behavior ignores the fusion of heterogeneous knowledge among behavior. However, we have noticed that heterogeneous user behavior contain rich semantic knowledge, and using semantics to represent and reason about user behavior can more effectively promote heterogeneous knowledge fusion and capture user interests. LLMs have shown remarkable capabilities in various fields, thanks to rich semantic knowledge and powerful inferential reasoning [1, 10]. We have designed a new user behavior modeling framework via LLM, which extracts and integrates heterogeneous knowledge from heterogeneous behavior information of users, and transforms structured user behavior into unstructured heterogeneous knowledge. In the field of recommendation, there have been some attempts to use LLM for personalized recommendation.

Recent advancements in Natural Language Processing (NLP) have led to the development of NLP-based recommender systems that have shown superior performance. However, current models commonly treat items as mere IDs and adopt discriminative modeling, resulting in limitations of (1) fully leveraging the content information of items and the language modeling capabilities of NLP models; (2) interpreting user interests to improve relevance and diversity; and (3) adapting practical circumstances such as growing item inventories. To address these limitations, we present GPT4Rec, a novel and flexible generative framework inspired by search engines. It first generates hypothetical "search queries" given item titles in a user's history, and then retrieves items for recommendation by searching these queries. The framework overcomes previous limitations by learning both user and item embeddings in the language space. To well-capture user interests with different aspects and granularity for improving relevance and diversity, we propose a multi-query generation technique with beam search. The generated queries naturally serve as interpretable representations of user interests and can be searched to recommend cold-start items. With GPT-2 language model and BM25 search engine, our framework outperforms state-of-the-art methods by $75.7\%$ and $22.2\%$ in Recall@K on two public datasets. Experiments further revealed that multi-query generation with beam search improves both the diversity of retrieved items and the coverage of a user's multi-interests. The adaptiveness and interpretability of generated queries are discussed with qualitative case studies.

Many projects (both practical and academic) have designed algorithms to match users to content they will enjoy under the assumption that user's preferences and opinions do not change with the content they see. Evidence suggests that individuals' preferences are directly shaped by what content they see -- radicalization, rabbit holes, polarization, and boredom are all example phenomena of preferences affected by content. Polarization in particular can occur even in ecosystems with "mass media," where no personalization takes place, as recently explored in a natural model of preference dynamics by~\citet{hkazla2019geometric} and~\citet{gaitonde2021polarization}. If all users' preferences are drawn towards content they already like, or are repelled from content they already dislike, uniform consumption of media leads to a population of heterogeneous preferences converging towards only two poles. In this work, we explore whether some phenomenon akin to polarization occurs when users receive \emph{personalized} content recommendations. We use a similar model of preference dynamics, where an individual's preferences move towards content the consume and enjoy, and away from content they consume and dislike. We show that standard user reward maximization is an almost trivial goal in such an environment (a large class of simple algorithms will achieve only constant regret). A more interesting objective, then, is to understand under what conditions a recommendation algorithm can ensure stationarity of user's preferences. We show how to design a content recommendations which can achieve approximate stationarity, under mild conditions on the set of available content, when a user's preferences are known, and how one can learn enough about a user's preferences to implement such a strategy even when user preferences are initially unknown.

Recommender systems are among the most pervasive machine learning applications on the Internet. Social media, audio and video streaming, news, and e-commerce are all heavily driven by the data-intensive personalization they enable, leveraging information drawn from the behavior of large user bases to offer a myriad of recommendation services. Point of Interest (PoI) recommendation is the task of recommending locations (business, cultural sites, natural areas) for a user to visit. This is a well-established sub-field within recommender systems, and as a domain of application, it provides a good introduction to the challenges of applying personalized recommendation in practical contexts. An effective PoI recommender must consider a user's interests and preferences, as in any personalized system, but also practical aspects of travel: weather, congestion, hours of operation, seasonality, to name a few.

We are 100% focused on customer success, so we only get paid if we get you a sale. Our solution is actually free for you. There is no CPC, or set up fee. We just charge a small fee for every product we help you to sell. This is how it works: we connect a tracking pixel to every product we recommend, at the end of the month, we will send you an invoice for the products that users have bought using RecoMind.

Recommender systems are widely developed to learn user preferences from their past history and make predictions on the unseen items a user may like. User preferences in the form of absolute preferences, such as user ratings or clicks are commonly used to model a user’s interest and generate recommendations. However, rating items is not the most natural mechanism that users use for making decisions in daily life. For instance, we do not rate t-shirts when we want to buy one. It is more likely that we will compare them one to one, and purchase the preferred one. In this work, we focus on relative feedback, which generates pairwise preferences as an alternative way to model user preferences and compute recommendations. In our scenario, each user is shown a set of item pairs and asked to compare them to indicate which item in the pair is more preferred. We propose a recommendation algorithm to predict a user’s relative preference for a given pairs of items and compute a personalised ranking of items. We demonstrate the effectiveness of our proposed algorithm in comparison with state-of-the-art relative feedback based recommendation approaches. Our experimental results reveal that the proposed algorithm is able to outperform the baseline algorithms on popular ranking-oriented evaluation metrics.

We investigate the problem of fair recommendation in the context of two-sided online platforms, comprising customers on one side and producers on the other. Traditionally, recommendation services in these platforms have focused on maximizing customer satisfaction by tailoring the results according to the personalized preferences of individual customers. However, our investigation reveals that such customer-centric design may lead to unfair distribution of exposure among the producers, which may adversely impact their well-being. On the other hand, a producer-centric design might become unfair to the customers. Thus, we consider fairness issues that span both customers and producers. Our approach involves a novel mapping of the fair recommendation problem to a constrained version of the problem of fairly allocating indivisible goods. Our proposed FairRec algorithm guarantees at least Maximin Share (MMS) of exposure for most of the producers and Envy-Free up to One item (EF1) fairness for every customer. Extensive evaluations over multiple real-world datasets show the effectiveness of FairRec in ensuring two-sided fairness while incurring a marginal loss in the overall recommendation quality.

LTCV stands for lifetime customer value i.e. a customer's timeframe of association with the business. Maximizing #customer_lifetime_value is important with #personalized_recommendation so that customers can keep coming and shopping on your e-store. The widget can be added to the accounts page so that customer can easily opt for re-purchase. Another widget- "More of your Choice" includes the products similar to those that customer has already purchased. This also helps in understanding the preferences of your customer.