Thanks to visit codestin.com
Credit goes to www.scribd.com

Scribd
Upload
18 views2 pages

Sales Forecasting Using Time Series Analysis

The document outlines a project focused on forecasting future sales using time series analysis to aid businesses in planning. It details the process of data collection, preprocessing, exploratory data analysis, and modeling with ARIMA, SARIMA, and Prophet models, concluding that the SARIMA model performed best. Future improvements include incorporating external variables and deploying the model via a Flask API for visualization.

Uploaded by

swaminathanvm3
Copyright
© © All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as PDF, TXT or read online on Scribd
18 views2 pages

Sales Forecasting Using Time Series Analysis

The document outlines a project focused on forecasting future sales using time series analysis to aid businesses in planning. It details the process of data collection, preprocessing, exploratory data analysis, and modeling with ARIMA, SARIMA, and Prophet models, concluding that the SARIMA model performed best. Future improvements include incorporating external variables and deploying the model via a Flask API for visualization.

Uploaded by

swaminathanvm3
Copyright
© © All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as PDF, TXT or read online on Scribd
You are on page 1/ 2

Sales Forecasting Using Time Series Analysis

### Project Title: Sales Forecasting Using Time Series Analysis

**Objective:**

To forecast future sales using time series models, helping businesses in inventory planning, staffing,

and budgeting.

**Introduction:**

Forecasting sales is a common requirement across industries. Time series analysis helps in

understanding trends, seasonality, and future values.

**Data Collection:**

Data was collected from a retail company showing daily sales of multiple products across stores.

**Data Preprocessing:**

- Fill missing values using forward filling.

- Convert date columns into datetime objects.

- Resample to weekly or monthly for stability.

**EDA and Visualization:**

- Plot time series to observe seasonality and trends.

- Use rolling means and differencing.

**Modeling:**

- ARIMA, SARIMA, and Prophet models were used.


- Evaluate using Mean Absolute Error (MAE) and RMSE.

**Results:**

- SARIMA model gave the best performance with lowest RMSE.

- Forecasts aligned well with known seasonal events.

**Conclusion:**

The SARIMA model is effective for this retail sales dataset. It offers valuable foresight for business

planning.

**Future Improvements:**

- Add external variables like promotions, holidays.

- Deploy model using Flask API and visualize in dashboard.

You might also like