Tabular Regression
Scikit-learn
English
scikit-learn
random-forest
retail
demand-forecasting
inventory-management
Instructions to use jerewy/Model_NexusCrew with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Scikit-learn
How to use jerewy/Model_NexusCrew with Scikit-learn:
from huggingface_hub import hf_hub_download import joblib model = joblib.load( hf_hub_download("jerewy/Model_NexusCrew", "sklearn_model.joblib") ) # only load pickle files from sources you trust # read more about it here https://skops.readthedocs.io/en/stable/persistence.html - Notebooks
- Google Colab
- Kaggle
Commit History
-
Update README.md
Verified signaturec23983b -
Update README.md
Verified signaturedfbe5de -
Update README.md
Verified signature811aca8 -
Update README.md
Verified signature# Smart Inventory Advisor for Retail Sales This repository contains a machine learning project that analyzes retail sales data to provide actionable inventory management recommendations. The primary goal is to help a store owner identify which products to restock and how many units to order, based on a data-driven sales forecast. This project was developed for the Datathon Nexus Crew. ## Project Overview The project follows a complete machine learning workflow: 1. **Exploratory Data Analysis (EDA):** Initial analysis to understand trends, patterns, and relationships within the data. 2. **Preprocessing & Feature Engineering:** Cleaning the data, converting categorical features to numerical values, and creating new time-based features from dates. 3. **Model Training & Tuning:** Building a `RandomForestRegressor` to predict actual `Units Sold`. The model was tuned using `RandomizedSearchCV` to improve its reliability and prevent overfitting. 4. **Actionable Recommendations:** …c730800 -
Update README.md
Verified signature# Smart Inventory Advisor for Retail Sales This repository contains a machine learning project that analyzes retail sales data to provide actionable inventory management recommendations. The primary goal is to help a store owner identify which products to restock and how many units to order, based on a data-driven sales forecast. This project was developed for the Datathon Nexus Crew. ## Project Overview The project follows a complete machine learning workflow: 1. **Exploratory Data Analysis (EDA):** Initial analysis to understand trends, patterns, and relationships within the data. 2. **Preprocessing & Feature Engineering:** Cleaning the data, converting categorical features to numerical values, and creating new time-based features from dates. 3. **Model Training & Tuning:** Building a `RandomForestRegressor` to predict actual `Units Sold`. The model was tuned using `RandomizedSearchCV` to improve its reliability and prevent overfitting. 4. **Actionable Recommendations:** …702fe68 -
Upload best_sales_model.pkl
Verified signatured3f8b87 -
initial commit
Verified signaturea0bb3d8