BestHub
Sign in
Didi Tech
Author

Didi Tech

Official Didi technology account

296
Articles
0
Likes
672
Views
0
Comments
Recent Articles

Latest from Didi Tech

100 recent articles max
Didi Tech
Didi Tech
Jun 4, 2021 · Artificial Intelligence

Graph Convolutional Network for Shared Bike Demand Forecasting: Time Series Modeling and Multi‑Task Learning

The paper presents a graph convolutional network approach that leverages multi‑task learning and spectral graph convolutions to forecast shared‑bike inflow, outflow, and demand gaps across a city’s non‑Euclidean parking network, demonstrating improved accuracy over traditional time‑series baselines while noting scalability and directional graph limitations.

GCNMulti-Task Learningdemand forecasting
0 likes · 13 min read
Graph Convolutional Network for Shared Bike Demand Forecasting: Time Series Modeling and Multi‑Task Learning
Didi Tech
Didi Tech
May 25, 2021 · Industry Insights

Becoming a Technical Superstar: Patterns, Deliberate Practice, and Persistence

The article shares a senior DiDi engineer's perspective on how engineers can overcome growth anxiety, adopt deliberate practice, build deep domain knowledge through work‑centered learning, and persistently refine coding and troubleshooting skills to become true technical leaders.

Learning Methodologycareer growthdeliberate practice
0 likes · 16 min read
Becoming a Technical Superstar: Patterns, Deliberate Practice, and Persistence
Didi Tech
Didi Tech
May 21, 2021 · Fundamentals

Introduction to Causal Inference and Its Application in Ride‑Hailing Business

The article introduces causal inference for ride‑hailing businesses, explaining the difference between causality and correlation, common misconceptions, and how randomized experiments and observational techniques like propensity‑score matching can quantify effects of actions such as coupons, driver assignments, and platform growth decisions.

Data AnalysisRide Hailingbusiness decision
0 likes · 7 min read
Introduction to Causal Inference and Its Application in Ride‑Hailing Business
Didi Tech
Didi Tech
May 19, 2021 · Artificial Intelligence

Applying Epsilon‑Greedy Bandit Algorithm for Content Delivery Optimization at DiDi

DiDi applied the epsilon‑greedy bandit algorithm integrated with its CMS to optimize ad placement across 600 slots, using quality scores, traffic sampling, and a drag‑and‑drop UI, which boosted CTR from 1.35% to 13.43% and unique visitors by 686%, demonstrating data‑driven growth beyond simple A/B testing.

Content OptimizationEpsilon-GreedySampling
0 likes · 10 min read
Applying Epsilon‑Greedy Bandit Algorithm for Content Delivery Optimization at DiDi
Didi Tech
Didi Tech
May 18, 2021 · R&D Management

Growth Journeys of Didi Ride-Hailing Engineers: From New Graduates to Technical Leaders

The article follows three Didi Ride‑Hailing engineers who joined in 2016 as fresh PhDs, detailing how they leveraged machine‑learning, dynamic dispatch, and product‑line automation to rise from junior developers to technical leaders, highlighting the blend of hard coding, soft communication, rapid‑learning culture, and the team’s current senior‑role hiring drive.

DidiDispatch algorithmR&D management
0 likes · 10 min read
Growth Journeys of Didi Ride-Hailing Engineers: From New Graduates to Technical Leaders
Didi Tech
Didi Tech
May 17, 2021 · Backend Development

Implementation of JSValue in JavaScript Engines: Tagged, Boxing, and Pointer Techniques

The article surveys how major JavaScript engines represent the dynamic JSValue type—using QuickJS’s tagged unions, JavaScriptCore’s NaN‑boxing, SpiderMonkey’s nun‑/pun‑boxing, V8’s tagged pointers with compression, and iOS’s Objective‑C pointer tags—explaining each scheme’s memory layout, performance trade‑offs, and design rationale.

JSValueJavaScript EngineTagged Pointer
0 likes · 11 min read
Implementation of JSValue in JavaScript Engines: Tagged, Boxing, and Pointer Techniques
Didi Tech
Didi Tech
May 14, 2021 · Backend Development

Bay Flow Platform: Service‑Side API Architecture and Evolution at DiDi

DiDi’s Bay Flow platform transforms its service‑side API into a configurable, layered “travel middle‑platform” that routes front‑end requests through a flow layer and reusable ability components, using the Dukang framework’s transports, steps, and factors to support dozens of ride‑hailing categories across PHP and Go while ensuring isolation and high reuse.

Dukang frameworkPHPbackend architecture
0 likes · 15 min read
Bay Flow Platform: Service‑Side API Architecture and Evolution at DiDi
Didi Tech
Didi Tech
May 11, 2021 · Artificial Intelligence

Continuous Causal Forest: Extending Uplift Modeling to Multi‑dimensional Continuous Treatments in Ride‑hailing Pricing

By extending binary causal forests with a Continuous Average Partial Effect statistic, the Continuous Causal Forest enables uplift modeling for multi‑dimensional continuous treatments such as ride‑hailing pricing, delivering superior Qini scores and over 15% ROI improvement while simplifying implementation and reducing deployment costs.

continuous treatmentpricing strategyrandom forest
0 likes · 10 min read
Continuous Causal Forest: Extending Uplift Modeling to Multi‑dimensional Continuous Treatments in Ride‑hailing Pricing
Didi Tech
Didi Tech
Apr 29, 2021 · Artificial Intelligence

Design and Architecture of DiDi Driver-side Intelligent Voice Assistant "XiaoDi"

The document details DiDi’s driver‑side intelligent voice assistant “XiaoDi,” describing its three‑layer architecture—audio source switching controller, semantic‑parsing core, and business API—along with conflict‑resolution mechanisms, multi‑turn dialogue handling, and a four‑region UI design that together enhance driver safety, convenience, and well‑being.

AIDriver AppSpeech Recognition
0 likes · 30 min read
Design and Architecture of DiDi Driver-side Intelligent Voice Assistant "XiaoDi"