Deep Learning for Expired POI Detection at Amap: Feature Engineering, RNN, Wide&Deep, and Attention‑TCN

This article details how Amap leverages deep‑learning techniques—including temporal and auxiliary feature engineering, multi‑stage RNN models, Wide&Deep architectures, and an Attention‑TCN approach—to accurately identify and handle expired points of interest, improving map freshness and user experience.

Deep LearningPOI expirationRNN

0 likes · 13 min read

Deep Learning for Expired POI Detection at Amap: Feature Engineering, RNN, Wide&Deep, and Attention‑TCN

Amap Tech

May 8, 2020 · Artificial Intelligence

Expired POI Detection in Amap Using Deep Learning: Feature Engineering, RNN, Wide&Deep, and TCN Models

The project develops a deep‑learning pipeline for Amap’s expired POI detection that integrates two‑year temporal trend features, industry and verification attributes, a variable‑length LSTM, a Wide‑Deep architecture, and a Wide‑Attention Temporal Convolutional Network, achieving higher accuracy and efficiency while outlining future macro‑and micro‑level enhancements.

Deep LearningPOI expirationRNN

0 likes · 15 min read

Expired POI Detection in Amap Using Deep Learning: Feature Engineering, RNN, Wide&Deep, and TCN Models

Amap Tech

Aug 6, 2019 · Artificial Intelligence

Boosting ETA Accuracy: How TCN Improves Historical Speed Prediction for Navigation

To enhance estimated arrival times in navigation, this article analyzes the shortcomings of traditional historical average methods and proposes a machine‑learning solution using Temporal Convolutional Networks combined with dynamic and static feature engineering, demonstrating reduced bad‑case rates and better handling of seasonal patterns.

ETA predictionTCNTime Series

0 likes · 11 min read

Boosting ETA Accuracy: How TCN Improves Historical Speed Prediction for Navigation