DMway was among a select group of Automated Machine Learning (AML) platforms recently profiled by Data Science Central‘s William Vorhies. Here’s what Data Science Central reported:
I had the pleasure of a demo and conversation with DMWay CEO Gil Nizri and CTO Ronen Meiri. They have elected to pursue an ultra-simple but sophisticated approach targeting non-data scientists. DMWay offers only GLM as a modeling tool and has developed a nice suite of preprocessing and feature selection tools to round out their easy-to-use platform. Their focus at least initially is on regulated markets (banking, insurance and lending) where interpretability is key and the volume of models is high, but looks to expand into all types of users.
- Blending: no, starts with analytic flat file.
- Cleanse: yes
- Impute and Transform: yes
- Feature Engineering: Some. More sophisticated automatic creation of for example ratios from related variables is to follow.
- Feature Selection: yes
- Select ML Algorithms to be utilized: Only GLM, selection of linear or logistic.
- Create Ensembles: no.
- Run Algorithms in Parallel: no, only one algorithm to run.
- Adjust Algorithm Hyperparameters during model development: yes – some access to adjust these for knowledgeable users.
- Select and deploy: Only a single champion model is presented. Deploy via R, Java, or SQL.