Stock Prediction and Quantitative Analysis Based on Machine Learning Method The project has set up a complete investment system pipeline based on the multifactor and machine learning model. The system mainly includes the process of data preparation, model selection and strategy generation. The workflow is to use the data of the whole year before the current time as the training set and implement the optimized XGBoost model to predict the stock return yield of the next month at the current time, after which selecting the top 50 stocks that most likely to rise in the next month for equal weight investment. And then employ the automated trading system to automatically maintain the portfolio on the designated trading day. The project composed of report (report.pdf) and codes. Abstract The stock market is affected by many factors which leads to drastic internal changes that are hard to predict. With the rapid development of the stock market, large quantities of data have been generated concerning stocks, which are suitable for implementing machine learning methods to analyze and learn fro

⚠ No verified equity curve — no track-record source connected.

No score history is stored yet — only the current score is shown.

⚠ No live verification account connected — ask for proof before buying.

Alerts on changes: coming soon

Prop-firm compatibility not provided.

Data-completeness & trust index (not a profitability rating)