%0 Generic %1 lam2017button %A Lam, Hoang Thanh %A Thiebaut, Johann-Michael %A Sinn, Mathieu %A Chen, Bei %A Mai, Tiep %A Alkan, Oznur %D 2017 %K automated automl button engineering feature machine one relational solvatio %T One button machine for automating feature engineering in relational databases %U http://arxiv.org/abs/1706.00327 %X Feature engineering is one of the most important and time consuming tasks in predictive analytics projects. It involves understanding domain knowledge and data exploration to discover relevant hand-crafted features from raw data. In this paper, we introduce a system called One Button Machine, or OneBM for short, which automates feature discovery in relational databases. OneBM automatically performs a key activity of data scientists, namely, joining of database tables and applying advanced data transformations to extract useful features from data. We validated OneBM in Kaggle competitions in which OneBM achieved performance as good as top 16% to 24% data scientists in three Kaggle competitions. More importantly, OneBM outperformed the state-of-the-art system in a Kaggle competition in terms of prediction accuracy and ranking on Kaggle leaderboard. The results show that OneBM can be useful for both data scientists and non-experts. It helps data scientists reduce data exploration time allowing them to try and error many ideas in short time. On the other hand, it enables non-experts, who are not familiar with data science, to quickly extract value from their data with a little effort, time and cost.

@misc{lam2017button, abstract = {Feature engineering is one of the most important and time consuming tasks in predictive analytics projects. It involves understanding domain knowledge and data exploration to discover relevant hand-crafted features from raw data. In this paper, we introduce a system called One Button Machine, or OneBM for short, which automates feature discovery in relational databases. OneBM automatically performs a key activity of data scientists, namely, joining of database tables and applying advanced data transformations to extract useful features from data. We validated OneBM in Kaggle competitions in which OneBM achieved performance as good as top 16% to 24% data scientists in three Kaggle competitions. More importantly, OneBM outperformed the state-of-the-art system in a Kaggle competition in terms of prediction accuracy and ranking on Kaggle leaderboard. The results show that OneBM can be useful for both data scientists and non-experts. It helps data scientists reduce data exploration time allowing them to try and error many ideas in short time. On the other hand, it enables non-experts, who are not familiar with data science, to quickly extract value from their data with a little effort, time and cost.}, added-at = {2019-01-09T09:49:45.000+0100}, author = {Lam, Hoang Thanh and Thiebaut, Johann-Michael and Sinn, Mathieu and Chen, Bei and Mai, Tiep and Alkan, Oznur}, biburl = {https://www.bibsonomy.org/bibtex/25ae481be51cba12be1af38d628824b0a/thoni}, description = {One button machine for automating feature engineering in relational databases}, interhash = {b0caed6f342bfc1325d4cff1bbe8783c}, intrahash = {5ae481be51cba12be1af38d628824b0a}, keywords = {automated automl button engineering feature machine one relational solvatio}, note = {cite arxiv:1706.00327}, timestamp = {2019-01-09T09:50:24.000+0100}, title = {One button machine for automating feature engineering in relational databases}, url = {http://arxiv.org/abs/1706.00327}, year = 2017 }