An AI co-pilot for the financial well-being of Indonesia's gig drivers.

Fairleap AI is an AI-powered financial well-being platform built for Gojek / GoTo ride-hailing and delivery drivers. It turns a driver's raw, irregular trip data into clear earnings insights, personalized financial guidance, and wellness support — helping drivers move from day-to-day income uncertainty toward long-term financial stability.

The name says it all: a fair leap forward for the gig workers who keep Indonesia moving.

Gig-economy drivers are the backbone of Indonesia's on-demand economy, yet they face structural challenges that traditional financial tools ignore:

• Income uncertainty — earnings swing daily with demand, weather, surge pricing, and hours worked, making it nearly impossible to budget or plan ahead.
• No financial visibility — drivers rarely have tools to understand why they earn what they earn, or how to optimize their working hours.
• Limited access to financial advice — conventional financial advisory and investment products are not designed for variable, cash-based gig income.
• Well-being is overlooked — long hours on the road create fatigue and stress that directly affect both safety and earning capacity.

Fairleap AI combines machine-learning forecasting with Generative AI (RAG-powered) advisory to give every driver a personal financial and wellness assistant:

• 📊 Earnings Analytics & Forecasting — ML regression models (XGBoost / scikit-learn) analyze historical trip data to surface earning patterns and predict future earnings, so drivers know what to expect and when to drive.
• 🤖 AI Financial Advisor — a Generative AI advisor (powered by Alibaba Cloud Qwen via DashScope, with RAG grounding) delivers personalized financial tips tailored to each driver's income profile.
• 📈 Investment Guidance — an AI investment bot recommends suitable, easy-to-understand investment options for variable gig income.
• 🧘 Wellness Companion — an AI wellness assistant provides health, fatigue, and work-life-balance guidance to keep drivers safe and sustainable.
• 💬 Conversational Chatbot — a RAG-based chatbot answers driver questions in natural language, grounded in Fairleap's domain knowledge.
• 🖥️ Unified Dashboard — a clean web dashboard brings earnings, analytics, financial advice, and wellness together in one place.

🥇 Fairleap AI was built and submitted to the Alibaba Cloud Indonesia GenAI Hackathon 2025, where it was selected as a Top 12 Finalist.

The Alibaba Cloud Indonesia GenAI Hackathon 2025 is a national-scale Generative AI hackathon held on May 24–25, 2025 in Jakarta, Indonesia (Habitate, Kuningan). It is organized by Alibaba Cloud, the GoTo Group, and KOMDIGI (Indonesia's Ministry of Communication and Digital Affairs).

The competition challenges innovators across Indonesia to build impactful, real-world solutions using Generative AI on Alibaba Cloud — leveraging services such as the Qwen large language models via DashScope. It brings together developers, students, and startups to prototype GenAI applications that address tangible problems, with finalists pitching their solutions to a panel of industry judges.

Out of all participating teams, Fairleap AI advanced to the Top 12 Finalists, recognizing its use of Generative AI to tackle income uncertainty and well-being for Indonesia's gig-economy drivers.

• typescript: A strongly typed programming language that builds on JavaScript.
• react: A JavaScript library for building user interfaces using components.
• next: A React framework that enables functionality such as server-side rendering and static site generation.
• react-dom: Serves as the entry point to the DOM and server renderers for React.
• tailwindcss: A utility-first CSS framework for rapidly building custom designs.
• eslint: A pluggable linter tool for identifying and fixing problems in JavaScript code.
• @types/react / @types/react-dom: Type definitions for React and React DOM.
• @types/node: TypeScript type definitions for Node.js runtime.
• zod: A TypeScript-first schema declaration and validation library.
• react-hook-form: A library for managing form state and validation in React applications.
• @hookform/resolvers: Utility package for integrating schema validation libraries with React Hook Form.
• clsx: A utility for conditionally joining classNames together.
• class-variance-authority: A utility for creating reusable class names with variant support in Tailwind CSS.
• tailwind-merge: Utility to intelligently merge Tailwind CSS classes.
• tailwindcss-animate: A plugin that provides animation utilities for Tailwind CSS.
• postcss: A tool for transforming CSS with JavaScript plugins.
• eslint-config-next: ESLint shareable config recommended for Next.js projects.
• @eslint/eslintrc: ESLint configuration tooling for managing and extending ESLint rules.
• next-themes: A theme toggler for Next.js apps with dark mode support.
• @radix-ui/react- (Accordion, Dialog, Tooltip, etc.)**: A suite of low-level UI components built with accessibility and customization in mind.
• vaul: A dialog/modal component built on top of Radix UI primitives.
• lucide-react: An icon library for React that provides a consistent set of SVG icons.
• react-icons: Popular icon packs as React components.
• recharts: A composable charting library built on React components using D3 under the hood.
• react-resizable-panels: A set of flexible and resizable layout panels for React.
• react-day-picker: A flexible date picker component for React.
• cmdk: A command menu component for building fast, accessible command palettes in React.
• sonner: A lightweight and customizable toast notification library.
• gsap: A high-performance JavaScript animation library for creating complex animations with ease.
• embla-carousel-react: A performant and customizable carousel/slider library for React.
• @stagewise/toolbar-next: A customizable toolbar component optimized for Next.js apps.
• date-fns: A modern JavaScript date utility library that provides comprehensive, yet simple, date functions.
• input-otp: A component for handling one-time-password input fields with ease.

• scikit-learn: A robust machine learning library that provides simple and efficient tools for data mining and data analysis.
• pandas: A powerful data manipulation and analysis library offering labeled data structures and operations for manipulating numerical tables and time series.
• numpy: A foundational library for numerical computing in Python, supporting large, multi-dimensional arrays and matrices.
• matplotlib: A comprehensive library for creating static, animated, and interactive visualizations in Python.
• joblib: A library for lightweight pipelining and efficient serialization of Python objects, often used for persisting machine learning models.
• pillow: A user-friendly imaging library in Python that adds image processing capabilities to your applications.
• flask: A lightweight and flexible WSGI web application framework designed to get applications up and running quickly.
• gunicorn: A Python WSGI HTTP server for UNIX that's commonly used to serve Flask or Django web applications in production.
• xgboost: An optimized gradient boosting library designed to be highly efficient, flexible, and portable for supervised learning problems.
• dashscope: A Python SDK provided by Alibaba Cloud for interacting with large language models (Qwen) and other AI services.

• Node.js: A fast, event-driven JavaScript runtime built on Chrome’s V8 engine for building scalable network applications.
• Express.js: A minimal and flexible Node.js web application framework that provides a robust set of features for web and mobile applications.
• Docker: A platform for developing, shipping, and running applications inside lightweight containers to ensure consistency across environments.
• MongoDB: A NoSQL database designed for scalability and flexibility, storing data in JSON-like documents.

This project is licensed under the MIT License.