Here is an impressive application of Deep TDA image analysis from @datarefiner. This video was divided into frames, and each frame was segmented as images, showcasing how TDA works in video analysis.

Big step forward for root cause analysis in real-world applications! There’s a new method that will help identify the causes of a problem or event. It uses causal discovery, boosting trees together with TDA. This is crucial to enable root cause analysis in tasks like the following: • Fraud detection • Drug discovery • Customer behavior analysis • Energy and sustainability • Financial analysis and risk management • Failure analysis in engineering systems Topological data analysis (TDA), on the other hand, studies the topological properties of data sets. You can use TDA for clustering, classification, and anomaly detection. The team @datarefiner developed a new approach to integrating causal discovery with TDA segmentation, and they are getting the best results from anything in the market right now. For the first time, there's a tool where users can choose clusters and get a focused causal dependency graph. They use boosting trees to estimate causal effects in complex systems. They complement this approach with TDA by offering insights into potential causal pathways. With TDA, users can visualize and understand the relationship between variables. Most open-source systems struggle with categorical parameters or values with different scales. This new approach doesn’t have those problems. Look at the attached video to understand what you can do with this. Here is a link to a post with all of the details. It contains three detailed examples that will drive the idea home: datarefiner.com/feed/causali… Thanks to @datarefiner for sponsoring this post.