diff --git a/INFERENCE_README.md b/INFERENCE_README.md
index 03995e7..ea57518 100644
--- a/INFERENCE_README.md
+++ b/INFERENCE_README.md
@@ -1,38 +1,30 @@
-# OHLCV Predictor - Simple Inference
+# OHLCV Predictor - Inference (Quick Reference)
 
-Refactored for easy reuse in other projects.
+For full instructions, see the main README.
 
-## Usage
+## Minimal usage
 
 ```python
 from predictor import OHLCVPredictor
 
-predictor = OHLCVPredictor('model.json')
+predictor = OHLCVPredictor('../data/xgboost_model_all_features.json')
 predictions = predictor.predict(your_ohlcv_dataframe)
 ```
 
-## Files Needed
-
-Copy these 5 files to your other project:
-
-1. `predictor.py`
-2. `custom_xgboost.py`
-3. `feature_engineering.py`
-4. `technical_indicator_functions.py`
-5. `xgboost_model_all_features.json`
-
-## Data Requirements
-
 Your DataFrame needs these columns:
-- `Open`, `High`, `Low`, `Close`, `Volume`, `Timestamp`
+- `Timestamp`, `Open`, `High`, `Low`, `Close`, `Volume`, `log_return`
 
-## Dependencies
+Note: If you are only running inference (not training with `main.py`), compute `log_return` first:
 
+```python
+import numpy as np
+df['log_return'] = np.log(df['Close'] / df['Close'].shift(1))
 ```
-xgboost >= 3.0.2
-pandas >= 2.2.3
-numpy >= 2.2.3
-scikit-learn >= 1.6.1
-ta >= 0.11.0
-numba >= 0.61.2
-``` 
\ No newline at end of file
+
+## Files to reuse in other projects
+
+- `predictor.py`
+- `custom_xgboost.py`
+- `feature_engineering.py`
+- `technical_indicator_functions.py`
+- your trained model file (e.g., `xgboost_model_all_features.json`)
diff --git a/README.md b/README.md
index 39b8dc7..fd86d4a 100644
--- a/README.md
+++ b/README.md
@@ -1,2 +1,119 @@
 # OHLCVPredictor
 
+End-to-end pipeline for engineering OHLCV features, training an XGBoost regressor (GPU by default), and running inference via a small, reusable predictor API.
+
+## Quickstart (uv)
+
+Prereqs:
+- Python 3.12+
+- `uv` installed (see `https://docs.astral.sh/uv/`)
+
+Install dependencies:
+
+```powershell
+uv sync
+```
+
+Run training (expects an input CSV; see Data Requirements):
+
+```powershell
+uv run python main.py
+```
+
+Run the inference demo:
+
+```powershell
+uv run python inference_example.py
+```
+
+## Data requirements
+
+Your input DataFrame/CSV must include these columns:
+- `Timestamp`, `Open`, `High`, `Low`, `Close`, `Volume`, `log_return`
+
+Notes:
+- `Timestamp` can be either a pandas datetime-like column or Unix seconds (int). During inference, the predictor will try to parse strings as datetimes; non-object dtypes are treated as Unix seconds.
+- `log_return` should be computed as:
+  ```python
+  df['log_return'] = np.log(df['Close'] / df['Close'].shift(1))
+  ```
+  The training script (`main.py`) computes it automatically. For standalone inference, ensure it exists before calling the predictor.
+- The training script filters out rows with `Volume == 0` and focuses on data newer than `2017-06-01` by default.
+
+## Training workflow
+
+The training entrypoint is `main.py`:
+- Reads the CSV at `../data/btcusd_1-min_data.csv` by default. Adjust `csv_path` in `main.py` to point to your data, or move your CSV to that path.
+- Engineers a large set of technical and OHLCV-derived features (see `feature_engineering.py` and `technical_indicator_functions.py`).
+- Optionally performs walk-forward cross validation to compute averaged feature importances.
+- Prunes low-importance and redundant features, trains XGBoost (GPU by default), and saves artifacts.
+- Produces charts with Plotly into `charts/`.
+
+Outputs produced by training:
+- Model: `../data/xgboost_model_all_features.json`
+- Results CSV: `../data/cumulative_feature_results.csv`
+- Charts: files under `charts/` (e.g., `all_features_prediction_error_distribution.html`)
+
+Run:
+```powershell
+uv run python main.py
+```
+
+If you do not have a CUDA-capable GPU, set the device to CPU (see GPU/CPU section).
+
+## Inference usage
+
+You can reuse the predictor in other projects or run the included example.
+
+Minimal example:
+
+```python
+from predictor import OHLCVPredictor
+import numpy as np
+
+predictor = OHLCVPredictor('../data/xgboost_model_all_features.json')
+
+# df must contain: Timestamp, Open, High, Low, Close, Volume, log_return
+log_returns = predictor.predict(df)
+prices_pred, prices_actual = predictor.predict_prices(df)
+```
+
+Run the comprehensive demo:
+
+```powershell
+uv run python inference_example.py
+```
+
+Files needed to embed the predictor in another project:
+- `predictor.py`
+- `custom_xgboost.py`
+- `feature_engineering.py`
+- `technical_indicator_functions.py`
+- your trained model file (e.g., `xgboost_model_all_features.json`)
+
+## GPU/CPU notes
+
+Training uses XGBoost with `device='cuda'` by default (see `custom_xgboost.py`). If you do not have a CUDA-capable GPU or drivers:
+- Change the parameter in `CustomXGBoostGPU.train()` from `device='cuda'` to `device='cpu'`, or
+- Pass `device='cpu'` when calling `train()` wherever applicable.
+
+Inference works on CPU even if the model was trained on GPU.
+
+## Dependencies
+
+The project is managed via `pyproject.toml` and `uv`. Key runtime deps include:
+- `xgboost`, `pandas`, `numpy`, `scikit-learn`, `ta`, `numba`
+- `dash`/Plotly for charts (Plotly is used by `plot_results.py`)
+
+Install using:
+```powershell
+uv sync
+```
+
+## Troubleshooting
+
+- KeyError: `'log_return'` during inference: ensure your input DataFrame includes `log_return` as described above.
+- Model file not found: confirm the path passed to `OHLCVPredictor(...)` matches where training saved it (default `../data/xgboost_model_all_features.json`).
+- Empty/old charts: delete the `charts/` folder and rerun training.
+- Memory issues: consider downcasting or using smaller windows; the code already downcasts numerics where possible.
+
diff --git a/main.py b/main.py
index d1c4380..3acdeff 100644
--- a/main.py
+++ b/main.py
@@ -272,7 +272,8 @@ if __name__ == '__main__':
         # )
         model.save_model(f'../data/xgboost_model_all_features.json')
 
-        test_preds = model.predict(X_test)
+        X_test_kept = df[kept_feature_cols].values.astype(np.float32)[split_idx:]
+        test_preds = model.predict(X_test_kept)
         rmse = np.sqrt(mean_squared_error(y_test, test_preds))
 
         # Reconstruct price series from log returns
@@ -322,7 +323,8 @@ if __name__ == '__main__':
         print(f'Cumulative feature run failed: {e}')
     print(f'All cumulative feature runs completed. Results saved to {results_csv}')
 
-    plot_prefix = f'all_features'
-    plot_prediction_error_distribution(predicted_prices, actual_prices, prefix=plot_prefix)
+    if 'predicted_prices' in locals() and 'actual_prices' in locals():
+        plot_prefix = f'all_features'
+        plot_prediction_error_distribution(predicted_prices, actual_prices, prefix=plot_prefix)
 
     sys.exit(0)
\ No newline at end of file