vaibhavmagon / FB-Ads-Opt-UCB

The easiest way to optimize Facebook Ads using Upper Confidence Bound Algorithm. 💻

Facebook Ads Optimisation Script Using Real Life Ads 💻

This code analyzes 43 Facebook ad sets and helps find the best ad set using the Upper Confidence Bound machine learning algorithm.

More on UCB here: http://banditalgs.com/2016/09/18/the-upper-confidence-bound-algorithm/

To Run

1. Export Ad set from Facebook ads directly for Impressions : Signups (Can use it for other data points as well).
2. Replace the data in ads-data.csv with current ads data.
3. Run: sudo python fb-ucb-ads.py

Data

Folder contains the ads-data.csv file with Ads Impressions : Signups data.

Ads Histogram for current Data

Clearly Ad: 2 is the winner and should have higher budget allocation.

Prerequisits

• Python 2.7
• Machine learning libraries
• Anaconda/Spyder

Contributers

• Vaibhav Magon