The NicePerf team, after clinching the top spot in the Tianchi DeepRec CTR model performance competition, shares a detailed walkthrough of their CPU‑only training optimizations—including operator selection, custom C++ kernels, and workflow tweaks—that cut overall training time by over a third.
This article presents a comprehensive study on estimating video ad attractiveness by analyzing 3‑second completion rates, proposing pairwise MLP and DeepFM models, introducing hierarchical sampling and multimodal features, and demonstrating practical deployment improvements in material recommendation and ad ranking.
This article explains how Tencent's advertising system leverages multimedia AI techniques—including multi‑armed bandit, pairwise learning, and DeepFM models—to automatically select optimal templates, music, and stickers for image and video assets, thereby reducing production cost, improving creative quality, and boosting ad performance.
This tutorial demonstrates how to use OpenMLDB together with OneFlow to build an end‑to‑end machine‑learning pipeline for predicting high‑potential JD users' purchase intent, covering environment setup, data loading, SQL table creation, offline feature extraction, DeepFM model training, model serving, online feature extraction, deployment, and real‑time inference.
The article describes how a logistics company built a data‑driven platform that uses big‑data storage, DeepFM and LSTM models, and real‑time GPS tracking to create an intelligent vehicle‑cargo matching system, a multi‑label driver tagging framework, and a freight price prediction engine, thereby improving efficiency and reducing costs across the industry.
This article describes how a logistics company built an intelligent, data‑driven platform that uses big‑data pipelines, DeepFM for cargo‑driver matching, LSTM for driver‑tag prediction, and cost‑aware models for freight‑price forecasting, improving efficiency and reducing operational costs.
This article explains how Tencent's Angel platform powers game recommendation on Steam, Wegame, and the Tesla platform, comparing traditional linear tag‑based and collaborative‑filtering methods with the non‑linear DeepFM model and offering practical deployment tips.
This article introduces Tencent's self‑developed Angel distributed machine‑learning platform and demonstrates how its recommendation algorithms, including classic linear models, collaborative filtering, and the non‑linear DeepFM model, are applied to game recommendation scenarios such as Steam, WeGame, and the Tesla platform.
This article presents a comprehensive overview of Du Xiaoman Financial's intelligent customer acquisition system, covering acquisition channels, efficiency improvements through multi‑stage models, data understanding with deepFM, the platform architecture, and related recruitment for senior machine‑learning engineers.
Meituan’s delivery ETA system progressed from linear regression to DeepFM, enriching user, rider, merchant, and spatiotemporal features, employing an asymmetric loss and business‑rule integration to favor early arrivals, adding a tail‑adjustment term, and is engineered with Spark‑assembled TFRecords, multi‑GPU TensorFlow training, and remote‑served TensorFlow Java inference achieving sub‑5 ms TP99 latency.
This article introduces the Wide&Deep, PNN, DeepFM, and a novel Wide‑ResNet model applied to Alibaba’s 1688 “You May Like” recommendation, describes the system architecture, training data, experimental results showing AUC improvements with batch normalization, and shares practical tuning insights.
