Forecasting Demand, Finding Sales Data - Facebook Prophet, Google Trends & Python

Channel support:
opensea.io/col...
If you like these videos, consider supporting the site by buying some of my artwork (it's cheap and helps encourage me to make more videos). If you do buy something, email me and I'll add you to my discord channel. Thanks!
Let's talk about forecasting demand, this is as old as money and commerce. Rainy season, you stock up on umbrellas; winter, winter coats, etc. I'll walk you through a simple example using open-source FBProphet in Python, one of the most powerful forecasting engines and also one of the easiest to use (once you manage to install it).
For source code:
www.viralml.co...
Stackline demand stats:
www.visualcapi...
Signup for my newsletter and more: www.viralml.com
Connect on Twitter: / amunategui
My books on Amazon:
Python Web Work - Prototyping Guide for Makers: Use HTML5 Templates, Serve Dynamic Content, Build Machine Learning Web Apps, Grow Audiences, Conquer the World
amzn.to/2veZtnB
MVP Light Stack Field Guide: Take Your Python MVP to the Web as Quickly and Cheaply as Possible:
amzn.to/2Q4Hiay
The Little Book of Fundamental Indicators: Hands-On Market Analysis with Python: Find Your Market Bearings with Python, Jupyter Notebooks, and Freely Available Data:
amzn.to/2DERG3d
Monetizing Machine Learning: Quickly Turn Python ML Ideas into Web Applications on the Serverless Cloud:
amzn.to/2PV3GCV
Grow Your Web Brand, Visibility & Traffic Organically: 5 Years of amunategui.github.Io and the Lessons I Learned from Growing My Online Community from the Ground Up:
amzn.to/2JDEU91
Fringe Tactics - Finding Motivation in Unusual Places: Alternative Ways of Coaxing Motivation Using Raw Inspiration, Fear, and In-Your-Face Logic
amzn.to/2DYWQas
Create Income Streams with Online Classes: Design Classes That Generate Long-Term Revenue:
amzn.to/2VToEHK
Defense Against The Dark Digital Attacks: How to Protect Your Identity and Workflow in 2019:
amzn.to/2Jw1AYS

[@MrJ17J]

You're a really good teacher. Even though I mainly use R as a marketing student, your videos offer creative and interesting insights.

[@viralml]

Most of these ideas can be translated into R and FBProphet has an R version as well. Thanks for the kind words!

[@camilaonofri2624]

Great explanation! The best I saw

[@anne-mariekiller7337]

Great video! Thanks Manuel!

[@viralml]

Thanks, Anne-Marie!

[@vasylcf]

Thanks 👍 It was useful and interesting video !

[@jaypdevaney]

This was a great video. It was very helpful. Thanks!

[@marcocerrato9014]

Amazing video. Thank you.

[@viralml]

Thanks, Marco!

[@freddylozano9262]

How do you use prophet model for where their is promotional price periods involved in the historical data? For instance, what if there was a frequent promotion on a consumer product that inflated demand, i.e. a box of cereal is normally $3.99, but then goes on sale for 2 weeks for a price point of $2.50. And this happens 13 times a year? That is what I am trying to solve for...

[@camilaonofri2624]

Hey! I'm facing a similiar problem. You don't want the model to learn from that history or behaviour, becasue it's been kind of manipulated. How did you solve it?

[@cristinagiraldo2725]

This was really nice. I have a quick question: is it possible to use prophet when I just have "year" in my dataset? Many thanks in advance.

[@viralml]

Not ideal - as it won't capture yearly cycles but if there's monthly or weekly cycles, that'll work.

[@cristinagiraldo2725]

@@viralml many thanks!

[@asesoriasdigitales]

Hi Manuel! Great video! What is the best way to measure accuracy? For example, get the MAE with -12 months? Thanks!

[@AllAboutJailbreak]

Is there a way to include google trends and combine it with own past sales data?

[@anwaraachati8504]

Very interesting thank you sir