-
diagram to show code execution order
-
Displays selected stocks' current prices, daily changes, and optimal portfolio weights.
-
Displays selected stocks' current prices, daily changes, and optimal portfolio weights.
About the Project 🔹 Inspiration This project was inspired by the idea of applying Genetic Algorithms (GA) to solve optimization problems that are difficult or impossible to solve with brute-force methods. Inspired by natural selection, GA mimics evolution to find near-optimal solutions in a reasonable time. 🔹 What I Learned • How to implement a Genetic Algorithm in Java step by step • The role of fitness functions in guiding optimization • How to handle crossover, mutation, and selection operators • Practical skills in structuring Java projects and working with version control (GitHub) 🔹 How I Built the Project 1. Defined the problem statement (optimization goal) 2. Implemented the Genetic Algorithm framework in Java ◦ Representation of individuals (chromosomes) ◦ Fitness function calculation ◦ Selection, crossover, mutation 3. Ran experiments with different parameters (population size, mutation rate, generations) 4. Collected and analyzed results to evaluate performance The core GA cycle can be summarized as: Populationt+1=Selection(Mutation(Crossover(Populationt))) Where: • Selection chooses the fittest individuals • Crossover combines parent genes • Mutation introduces diversity 🔹 Challenges Faced • Choosing the right fitness function was tricky — the algorithm’s success depends heavily on this. • Balancing exploration vs. exploitation (too much mutation = chaos, too little = stagnation). • Debugging issues with randomization and ensuring reproducibility. • Managing time efficiently within hackathon constraints.
Log in or sign up for Devpost to join the conversation.