|
--- |
|
language: |
|
- en |
|
library_name: sklearn |
|
tags: |
|
- Salespridiction |
|
- Regression |
|
- sklearn |
|
- bigmart |
|
license: apache-2.0 |
|
--- |
|
--- |
|
# Model Card for BigMart Sales Prediction Model |
|
|
|
## Model Details |
|
|
|
### Model Description |
|
|
|
This model is designed to predict sales for the BigMart dataset using a regression approach. It was trained using Scikit-Learn's `ExtraTreesRegressor` on features such as `Item_Weight`, `Item_Visibility`, `Item_Type`, and more. |
|
|
|
- **Developed by:** crudcook |
|
- **Model type:** Regression (Machine Learning) |
|
- **Language(s) (NLP):** Not applicable (it's a sales prediction model) |
|
|
|
|
|
### Model Sources |
|
|
|
- **Repository:** [BigMart Sales Prediction Model](https://huggingface.co/crudcook/Big_Mart_Sales_Prediction) |
|
- **Paper [optional]:** Not available |
|
- **Demo [optional]:** Not available |
|
|
|
## Uses |
|
|
|
### Direct Use |
|
The model can be directly used to predict sales figures for products based on features present in the BigMart dataset. |
|
|
|
### Downstream Use |
|
The model can be extended or fine-tuned for other retail sales prediction tasks if appropriate features are available. |
|
|
|
### Out-of-Scope Use |
|
Not suitable for NLP or other non-regression tasks. |
|
|
|
## Bias, Risks, and Limitations |
|
|
|
This model is trained on the BigMart dataset and may not generalize well to other datasets or industries. There could be inherent biases due to data collection, such as location-specific sales patterns. |
|
|
|
### Recommendations |
|
Users should evaluate the model's performance on their own datasets before using it for decision-making. |
|
|
|
## How to Get Started with the Model |
|
|
|
You can use the following code to load the model: |
|
|
|
```python |
|
from huggingface_hub import hf_hub_download |
|
import joblib |
|
|
|
repo_id = "crudcook/Big_Mart_Sales_Prediction" |
|
model_filename = "bigmart_sales_model.pkl" |
|
file_path = hf_hub_download(repo_id=repo_id, filename=model_filename) |
|
|
|
# Load the model |
|
model = joblib.load(file_path) |
|
|
|
# Example prediction (replace X_test with your test data) |
|
# predictions = model.predict(X_test) |
