Personal experiments on Reinforcement Learning

Optimal routing and delivery solutions using Google Maps and Python.

A detialed analysis on the customers, products, orders and shipments of the Brazilian E-commerce giant Olist.

A dynamic Python-based routing and package management system for optimizing delivery schedules and operations. Designed for WGUPS, it showcases efficient use of algorithms and data structures for real-world logistics solutions.

🚚 "2021 Huawei Delivery Optimization Competition" - Using a genetic model to minimize the multi-vehicle transportation cost with vehicle capacity constraints.（“2021华为配送优化竞赛” - 使用遗传算法在车辆运力限制下最小化多车辆的运输成本。）

Building a Semantic Delivery Coordination Engine

🚚 A genetic model written in Python for minimizing the delay time of delivery routes.（使用Python编写的用于最小化物流配送时间的遗传算法。）

Hermes Logistics - Fleet Management & Route Optimization

Business analytics & data visualization project analyzing Blinkit’s quick commerce model-delivery speed, urgency marketing, customer behavior, and revenue insights using Tableau.

University final project - "Веб-приложение для оптимизации авиамаршрутов доставки почтовых отправлений с использованием роевого интеллекта" (Grade A)

A delivery optimization project using causal inference and logistic optimization

A Python-based delivery optimization model using nearest neighbor heuristics for order grouping and route efficiency, with included CSV datasets and test results.

TypeScript based engine for optimally assigning delivery orders to riders using multi-stage optimization, intelligent batching, and dynamic surge handling.

End-to-end delivery analytics: SQL ops analysis, 37-feature ML model (94.77% accuracy), peak-hour insights, weather/traffic impact, production-ready predictions.

`ExternalIpAnalyzer.ps1` is a PowerShell script that processes ETL (Event Trace Log) files generated by Windows Delivery Optimization to extract external IP addresses and output them into a CSV file.

A high-performance Spring Boot application that solves the Vehicle Routing Problem (VRP) by optimally allocating delivery orders to a fleet of vehicles. It uses a custom Greedy Nearest-Neighbor Algorithm with the Haversine Formula to minimize total travel distance while strictly respecting priority tiers and vehicle capacity constraints.