Fabric Data Science Sales Forecasting: Predict sales numbers for product categories at a superstore.
Episode 48 of Fabric Espresso, hosted by Dr. Estera Kot.
About this episode
Text from the YouTube description.
The Synapse Data Science software as a service (SaaS) experience in Microsoft Fabric can help machine learning professionals build, deploy, and operationalize their machine learning models in a single analytics platform, while collaborating with other key roles. This article describes both the capabilities of the Synapse Data Science experience, and how machine learning models can address common business problems.
Join us in this Fabric Espresso episode as Amir and Estera discuss the Sales forecasting - predict sales numbers for product categories at a superstore.
🎙 Meet the Speakers:
👤 Guest Expert: Amir H. Jafari, PhD, Senior Product Manager | Fabric Data Science
LinkedIn: https://www.linkedin.com/in/ahjafari/
👤 Host: Estera Kot, PhD, Principal Product Manager at Microsoft.
LinkedIn: https://www.linkedin.com/in/esterakot/
Twitter: https://twitter.com/estera_kot
👍 Liked this video? Don't forget to hit the 'Like' button and share it with your peers!
🔔 Stay Updated: Subscribe to our channel for the latest in Microsoft Fabric Data Engineering, Data Science, and groundbreaking tech. Hit the notification bell to never miss out on the Fabric Espresso series!
Chapters
- 0:00 Introduction to fabric
- 1:13 Overview of data samples
- 2:59 Getting started prerequisites
- 3:24 Demo: Data loading and setup
- 5:37 Experiment configuration
- 6:55 Auto logging with mlflow
- 7:52 Exploratory data analysis
- 9:18 Data preprocessing
- 10:52 Time series resampling
- 13:09 Visualizing sales trends
- 14:32 Statistical decomposition
- 16:41 Training sarimax model
- 19:44 Model validation
- 21:00 Model logging and prediction
- 22:55 Business insights integration
- 25:56 Conclusion and partner work