https://github.com/abbaszaidi123/product-demand-forecasting-using-ml

https://github.com/abbaszaidi123/product-demand-forecasting-using-ml

ai mlops python testing training

Last synced: 6 months ago
JSON representation

• Host: GitHub
• URL: https://github.com/abbaszaidi123/product-demand-forecasting-using-ml
• Owner: abbaszaidi123
• Created: 2025-03-10T20:58:24.000Z (over 1 year ago)
• Default Branch: main
• Last Pushed: 2025-03-10T20:59:16.000Z (over 1 year ago)
• Last Synced: 2025-03-10T21:35:53.975Z (over 1 year ago)
• Topics: ai, mlops, python, testing, training
• Language: Jupyter Notebook
• Homepage:
• Size: 0 Bytes
• Stars: 0
• Watchers: 1
• Forks: 0
• Open Issues: 0
• Metadata Files:
  • Readme: README.md

Awesome Lists containing this project

README

          
# Demand Forecasting using Machine Learning

Demand forecasting is the process of making estimations about future customer demand over a defined period, using historical data and other information. 

Usually organisations follow tranditional forecasting techniques/algorithms such as Auto Arima, Auto Arima, Sarima, Simple moving average and many more.

## Table of Contents

- [Goal](#goal)

- [Workflow](#workflow)

- [Required Packages](#require)

## Goal 

Due to the recent boost in AI world, companies have started researching the possibility of using machine learning in place of tranditional approach.

Tuning traditional algorithms takes a significant amount of effords and domain expertise as well. 

In this repo, we are trying to figure out a way of predict the same using machine learning algorithms. 

## Data 

The dataset comprised of units sold on a daily basis along with details regarding the sales, eg. SKU(product id), Store, price etc.

*record_ID,	week,	store_id,	sku_id,	total_price,	base_price,	is_featured_sku,	is_display_sku,	units_sold*

## Workflow 

- Handling missing values

- Feature selection based on my previous experience in Supply chain domain

- Converting dataset into time series format to apply supervised learning approach.

- Regression Modeling

  - Random Forest

  - XGBoost

  - SVM (future scope)

- Hyperparameter Tuning

## Result

![train](https://github.com/shreyas-jk/Demand-Forecasting-Using-ML/blob/main/final.png?raw=true)

## Required Packages 

- numpy

- pandas

- sklearn

- easypreprocessing 

- seaborn 

- matplotlib

- xgboost