Skip to content

Forecast e-commerce sales with external variables using 3 different models and comparing their results

Notifications You must be signed in to change notification settings

algerza/ecommerce_time_series_forecast

Repository files navigation

alt text

E-commerce Sales Forecast

What is this project about?

In the dynamic landscape of e-commerce, accurately predicting units sold is crucial for ensuring optimal inventory management and maximizing revenue. Moreover, understanding the impact of marketing expenditure, especially during campaign periods, is essential for crafting effective strategies to drive sales and customer engagement.

In other words, imagine you're trying to predict the future sales of an online store. You know that past sales can give you hints about what's going to happen, but the sales data might be influenced by many things at once, like marketing campaigns, seasonal trends, or even random events.

By comparing forecasting models like VARIMA from DARTS library, Prophet by Meta, and ForecasterAutoreg from SKForecast, e-commerce businesses can unlock powerful insights into consumer behavior and market trends. These models offer sophisticated tools to analyze historical sales data alongside marketing initiatives, enabling businesses to forecast units sold with greater precision and anticipate the effects of marketing campaigns or web traffic trends on future sales. Through this comparative analysis, e-commerce stakeholders can enhance their predictive capabilities, optimize resource allocation, and make data-driven decisions that propel their businesses to success in the competitive online marketplace.

What data was used?

The data provided is synthetic and entirely fictitious. Consequently, it may not accurately reflect situations encountered in real e-commerce data. To simulate realistic scenarios, deliberate gaps have been introduced to mimic instances when servers were off or bugs occurred. While this notebook does not delve deeply into correcting imperfect datasets, I thought it may be useful to include these "effects" to make the fake data closer to reality.

About

Forecast e-commerce sales with external variables using 3 different models and comparing their results

Topics

Resources

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published