Upload algoDinero_gru_forecaster model - 2025-10-07 01:57:39
Browse files
README.md
ADDED
@@ -0,0 +1,78 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
---
|
2 |
+
license: mit
|
3 |
+
tags:
|
4 |
+
- fintech
|
5 |
+
- forecasting
|
6 |
+
- time-series
|
7 |
+
- financial
|
8 |
+
- gru
|
9 |
+
---
|
10 |
+
|
11 |
+
# Algodinero Gru Forecaster - Financial Time Series Forecasting Model
|
12 |
+
|
13 |
+
## Model Description
|
14 |
+
|
15 |
+
This is a GRU neural network model trained for financial time series forecasting. The model is part of the AlgoDinero FinTech Data Curation project and is designed to predict future stock prices and cryptocurrency values.
|
16 |
+
|
17 |
+
## Model Architecture
|
18 |
+
|
19 |
+
- **Model Type**: GRU
|
20 |
+
- **Input**: Time series of closing prices
|
21 |
+
- **Output**: Forecasted prices for future time steps
|
22 |
+
- **Training Data**: Multi-asset financial data (stocks and cryptocurrencies)
|
23 |
+
|
24 |
+
## Usage
|
25 |
+
|
26 |
+
```python
|
27 |
+
import torch
|
28 |
+
import numpy as np
|
29 |
+
from huggingface_hub import hf_hub_download
|
30 |
+
|
31 |
+
# Download model
|
32 |
+
model_path = hf_hub_download(repo_id="usairamsaeed/algoDinero_gru_forecaster", filename="model.pkl")
|
33 |
+
|
34 |
+
# Load model
|
35 |
+
with open(model_path, 'rb') as f:
|
36 |
+
model_data = pickle.load(f)
|
37 |
+
|
38 |
+
# Use with your forecasting pipeline
|
39 |
+
```
|
40 |
+
|
41 |
+
## Training Details
|
42 |
+
|
43 |
+
- **Training Period**: 365 days of historical data
|
44 |
+
- **Assets**: AAPL, TSLA, BTC-USD, ETH-USD, MSFT, GOOGL
|
45 |
+
- **Data Preprocessing**: Normalized using z-score normalization
|
46 |
+
- **Training Method**: Adam optimizer with MSE loss
|
47 |
+
|
48 |
+
## Model Performance
|
49 |
+
|
50 |
+
This model is part of an ensemble forecasting system that combines multiple approaches:
|
51 |
+
- Moving Average
|
52 |
+
- ARIMA
|
53 |
+
- VAR
|
54 |
+
- MLP
|
55 |
+
- GRU
|
56 |
+
- LSTM
|
57 |
+
- Transformer
|
58 |
+
|
59 |
+
The ensemble approach provides robust predictions by combining the strengths of different forecasting methods.
|
60 |
+
|
61 |
+
## Limitations
|
62 |
+
|
63 |
+
- Model performance depends on market conditions
|
64 |
+
- Historical performance does not guarantee future results
|
65 |
+
- Use for educational/research purposes
|
66 |
+
- Not intended for actual trading decisions
|
67 |
+
|
68 |
+
## Citation
|
69 |
+
|
70 |
+
```
|
71 |
+
@misc{algoDineroGru,
|
72 |
+
title={AlgoDinero GRU Financial Forecasting Model},
|
73 |
+
author={Usair Ahmad Saeed},
|
74 |
+
year={2025},
|
75 |
+
publisher={Hugging Face},
|
76 |
+
howpublished={\url{https://huggingface.co/usairamsaeed/algoDinero_gru_forecaster}}
|
77 |
+
}
|
78 |
+
```
|
model.pkl
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:11e93b4d3779fe492e21c8ebd5c103944efebf525410aa5b1758980c10e7b700
|
3 |
+
size 15660
|