Deep Learning for Tabular Data: A Bag of Tricks

DataRobot Employee
DataRobot Employee
2 0 529

Deep Learning has shown clear success in applications involving audio, video, images and, more recently, NLP (natural language processing). When considering Tabular Data, especially diverse or heterogeneous datasets, Deep Learning is often dismissed or else shown to fall short of more popular approaches such as XGBoost.

The difficulty of training deep learning models is often cited as a prime reason to avoid making use of the technique, which likely stems from the reality that default settings of your favorite framework likely won't produce a good model.

Recently there have been efforts to mitigate this issue with libraries such as FastAI and significant research on hyper optimization applied to neural networks; however, on many datasets accuracy still falls short, training time is computationally unreasonable, or a combination of the two. But don't lose hope: by taking a disciplined approach to tuning hyperparameters, leveraging some recent techniques, and building some intuition, Deep Learning can be a useful approach to learning heterogenous tabular data.

In this video (adapted from my ODSC Boston 2020 presentation), I share some findings and processes for implementing deep learning when learning heterogenous tabular data.

If you'd like to know more, let me know. Also, please share your own findings. (If you're interested, have a look at my article at, DataRobot’s Automated Deep Learning for Tabular Data.)

- Jason

BIG NEWS: The DataRobot Community is getting a new look!
Over the next few weeks, we'll be reorganizing some of our content to provide you with faster & easier help for your DataRobot questions. Stay tuned and look for more information in the upcoming DataRobot Community Newsletter.

See the quick index for learning resources and quick index for learning sessions to find links to some great learning content.

DataRobot 6.2 is Here!

Ready to see what some highlights of the latest DataRobot release? Have a look at DataRobot Release 6.2! And make sure to register today for the October 6th webinar where Richard will present an overview of the 6.2 headline features.