Skip to content

This project analyzes and forecasts Superstore sales data for furniture and office supplies using time series models like ARIMA and Facebook's Prophet, highlighting seasonal patterns and trends.

Notifications You must be signed in to change notification settings

AloRay/TIME-SERIES-ANALYSIS-AND-FORECASTING-SUPERSTORE-DATA

Repository files navigation

SUPERSTORE SALES FORECASTING

This project analyzes and forecasts Superstore sales data, focusing on furniture and office supplies categories. This project aims to analyze Superstore sales data and forecast future sales for furniture and office supplies. It identifies seasonal patterns, trends and predicts future sales using ARIMA and Prophet models.

Data Preparation

  • Load and preprocess Superstore sales data.
  • Filter data for furniture and office supplies categories.
  • Aggregate sales data by date.

Time Series Analysis

  • Visualize sales data to identify trends and seasonal patterns.
  • Decompose time series data to analyze components.

Forecasting Models

  • Fit ARIMA model to the sales data.
  • Fit Prophet model for more advanced forecasting.
  • Compare model performance using AIC.

Results

  • Visualize forecasts for both furniture and office supplies.
  • Identify key dates and trends from the forecasted data.

Conclusion This project successfully forecasts sales data, revealing valuable insights for business planning and decision-making in retail.

Requirements

  • Python 3.x
  • pandas
  • numpy
  • matplotlib
  • statsmodels
  • Facebook Prophet

About

This project analyzes and forecasts Superstore sales data for furniture and office supplies using time series models like ARIMA and Facebook's Prophet, highlighting seasonal patterns and trends.

Topics

Resources

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published