Stock Price Prediction for NVIDIA stocks
| Sl No | Status | Artifacts | Description | |
|---|---|---|---|---|
| 1 | ⏳ | Google Slides | Presentation slides | |
| 2 | ✅ | 1_NVDA_vs_Competitors.ipynb | Focus on the stock you pick and their competitors Report summary statistics of the training period you select and plot the kernel density |
|
| 3 | ✅ | 2_Feature_Mart.ipynb | Please use the features/factors you take and discovered e.g., FRED, Fama-French website, ADS, AR, CAPM, momentum factors, volume, price/return lags, etc. to construct a feature database The target variable Y can be either price or return Frequency could be either daily or monthly |
|
| 4 | ✅ | 3_Feature_Importance.ipynb | Virtualize the feature importance and feature selection process using regression based approach Ridge regression, LASSO, Elastic Net or LARS vs decision tree based approach (random forest, XGBoost) |
|
| 5 | ✅ | 4_Model_Training.ipynb | Proposed and train 3-6 models by feeding in the features you prepared in step 2 Compare the model performance using RMSE between the fitted Y and actual Y in testing period |
|
| 6 | ✅ | 5_Benchmark_Study.ipynb | Include one benchmark study that uses GARCH or Kalman Filter | |
| 7 | ⏳ | Compose of trading rules that uses buy-and-hold, long-short, or day trade | ||
| 8 | ⏳ | Generate trading signals using the above 3-6 models. Compare their PnL |
❗ Date Range to incldues
- Train Range = 2022-01-01 ~ 2023-07-31
- Predict Range = 2023-08-01 ~ 2023-11-01
📓 All notebooks are Colab compatible.
Local Setup
- Downloading Metadata Files
make download
React
Typescript
Django
Laravel
Facebook
Microsoft
Google
Alibaba
D3
Tencent