More than a year after announcing plans to automate the feature engineering phase of artificial intelligence projects, Seattle-based startup Kaskada Inc. is bringing its first product to market. Kaskada says it aims to democratize feature engineering, an often laborious process that requires data scientists to select, clean and validate the data to be fed into machine learning training models prior to moving them into production. A model intended to predict housing prices, for example, would be feature engineered with predictor data such as the square footage of properties, number of bedrooms and location. The larger and more complete the training data set, the better the results. The resources required to collect data and move machine learning models into production can be so significant that the capabilities are out of reach of all but the largest companies.

The Defense Advanced Research Projects Agency wants to make the process of training machine-learning models more efficient. Currently, training a ML model requires the test data be labeled, which requires humans identify an an image or specific phrases in text that the algorithm should learn to recognize. The more labeled data the system can review, the more complete its training and the better the eventual results. Amassing enough clean, consistently labeled data to train an algorithm is expensive and time consuming. If, for example, a company wants to analyze user reviews of its products, it will need "at least 90,000 reviews to build a model that performs adequately," according to AltexSoft, a software R&D engineering firm.