These COMAP MCM problem statements challenge teams to develop statistical models for pricing used sailboats using a large 2023 dataset and to propose innovative strategies for the Olympic Games, evaluating regional effects, data sources, and policy recommendations for sustainable hosting.
The article details the design and implementation of a content revenue settlement platform that aggregates traffic and ad data, uses a Spark‑plus‑PALO architecture for processing tens of millions of daily records, and employs a master‑worker model with idempotent tasks, temporary tables, and verification steps to ensure reliable monthly profit‑share calculations for authors, media, mini‑program owners, and users.
This article presents a bi‑objective inventory allocation model for guaranteed‑delivery advertising that simultaneously maximizes impressions for new orders and balances supply distribution, and introduces a fast alternating local‑search algorithm (BOLS) that outperforms popular multi‑objective evolutionary algorithms and the commercial solver Gurobi in extensive experiments.
This article describes how integrating causal inference with large language models and Retrieval‑Augmented Generation can automate and explain e‑commerce product pricing, detailing the three‑step workflow, reinforcement‑learning rewards, experimental results, and future directions for end‑to‑end RAG‑LLM training.
This article presents five peer‑reviewed papers accepted to the Kuaishou Community Science track at the 2023 ACM SIGIR conference, covering offline reinforcement learning for recommendation fairness, global residual value for fair item exposure, personalized QoE in short‑form video, multi‑behavior self‑supervised recommendation, and a search‑enhanced sequential recommendation framework.
Vivo tackles the complex problem of mixing heterogeneous content queues—ads, games, and organic items—in its information‑flow and app‑store by evolving from rule‑based weighting to Q‑learning and deep‑learning position models that respect product constraints, preserve ordering, and balance short‑term revenue with long‑term user experience, while planning deeper personalization and on‑device solutions.
This article introduces Multi-Attribution Learning (MAL), a novel paradigm that jointly models multiple attribution labels to overcome the single-attribution bottleneck in conversion rate (CVR) prediction, detailing its architecture, auxiliary tasks, extensive offline and online experiments, and significant business gains.
The paper outlines DiDi Food’s intelligent subsidy system, detailing economic foundations of differential pricing, a LightGBM‑based uplift prediction architecture, greedy and integer‑programming allocation methods, and experimental results that demonstrate substantial ROI gains, while proposing future enhancements such as real‑time features and reinforcement learning.
Deep GSP is a multi‑objective, deep‑learning ad auction that jointly learns rank scores while enforcing game‑theoretic constraints—monotonicity, incentive compatibility, and Nash equilibrium—and a smooth‑transition penalty, using DDPG reinforcement learning to outperform traditional GSP across revenue, clicks, conversions, and add‑to‑cart metrics.
This article presents a three‑part technical guide covering the fundamentals of computational advertising and real‑time bidding, detailed offline pCTR model training pipelines with feature engineering, calibration and model structure improvements, and advanced online learning techniques such as parameter freezing, sample replay and knowledge distillation, all aimed at boosting CTR performance and reducing bias in large‑scale ad platforms.
This article introduces recommendation ranking, breaks down its components, explains how to build ranking models, and provides additional insights, while also presenting the author's background and related job opportunities in the e‑commerce recommendation field.
This article details Meituan's interactive recommendation system for its food‑delivery homepage feed, covering the motivation, challenges, system architecture, user intent modeling, evaluation metrics, experimental results, and future directions, illustrating how real‑time, user‑centric recommendations improve conversion and user experience.
This article presents a comprehensive overview of Huya Live's recommendation system, covering business background, system architecture, vector retrieval techniques, ranking pipeline, technical challenges, implementation details, and future outlook, highlighting scalability and performance optimizations.
Daily Fresh built a custom address database and advanced LBS system—including location correction, trajectory denoising, and stay‑point analysis—to accurately detect and curb fake delivery sign‑offs, achieving over 96% detection accuracy and industry‑leading results.
The paper introduces Score‑Weighted VCG, a learning‑based ad auction framework that models externalities by learning a monotone scoring function and solving a weighted‑welfare matching problem, achieving incentive compatibility, individual rationality, and near‑optimal revenue and welfare on synthetic and large‑scale Taobao data.
The paper introduces Contextual Generative Auction (CGA), a generative framework that directly optimizes ad placements while modeling permutation‑level externalities, decouples allocation from payment learning, and achieves near‑optimal Myerson‑style outcomes, delivering up to 3.2% higher RPM, 1.4% more CTR, 6.4% GMV growth, and 3.5% increased advertiser ROI in large‑scale Taobao experiments.
The article categorizes global payment methods by continent and country, analyzing wallet, internet, mobile, card, prepaid, cross‑border, POS, offline and other payment dimensions, and presents visual breakdowns for Asia, Europe, and the rest of the world.
This article describes how a commercial search platform iteratively upgrades its system by structuring business knowledge into a knowledge graph, applying multi‑stage entity extraction (CRF, Electra‑CRF, GLM‑3, OCR), and leveraging large language models to improve relevance, user experience, and revenue.
This article reviews the development history, technical routes, and recent breakthroughs of pre‑ranking (coarse ranking) in large‑scale advertising systems, focusing on Alibaba's COLD (Computing‑power‑cost‑aware Online and Lightweight Deep) framework, its model design, engineering optimizations, experimental results, and future research directions.
This article models the chance of finding a job that simultaneously offers a high salary, light workload, and proximity to one’s hometown, using conditional probability and real‑world data to show why such an ideal position is extremely rare and how relaxing requirements dramatically improves the odds.
