October 26, 2018
Machine learning is becoming increasingly popular with TDWI audiences. Use cases include recommendation engines, fraud detection, churn analysis, predictive maintenance, cybersecurity, and identifying money laundering.
Although the technology behind machine learning has been around since the 1990s, the advent of big data has both revitalized it and increased the complexity of using these models to drive insight and action.
One of the biggest challenges facing companies that want to take advantage of machine learning is making the leap from the training phase to full production. Data engineers must create robust production data pipelines to feed machine learning models the increasing amounts of disparate data they require.
This TDWI Checklist Report discusses best practices for data engineering and management to support machine learning with a focus on collecting, cleansing, transforming, and governing new types of data for analysis.