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.

Gen AI–powered sprint risk analysis prototype for Technical Program Management. Simulates automated detection of delivery blockers and cross-team dependencies, demonstrating potential to reduce manual status review time by ~30–40% and improve early risk visibility in engineering programs

🚚 "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。）

Enterprise monitoring solution for Windows Delivery Optimization. Collects per-job DO telemetry from Intune-managed devices via Proactive Remediations, ingests through Azure Functions + Service Bus, and visualizes in Log Analytics with Workbooks and Alert Rules. Full Bicep IaC and automated deployment.

Hermes Logistics - Fleet Management & Route Optimization

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。）

Live trace collector for Intune Company Portal Win32/MSIX/LOB app deployments. Captures baseline, network trace, IME log delta, time-filtered event logs, and content-distribution stack (WinGet/DO/WU) into an ODC-compatible ZIP.

A machine learning-powered platform to accurately predict delivery times in hyperlocal logistics by fusing Google Maps, live weather, and historical trip data.

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

Engineering leadership playbook covering delivery standards, flow metrics, Agile practices, AI in SDLC, and scalable team governance.

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

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

Smart route optimization platform for Delhi Metro & DTC buses with interactive maps, fare calculator, crowd analytics, and OAuth admin dashboard.

Delivery routing & fleet scheduling engine in C++ — A*, Yen's K-Shortest Paths, TSP heuristic