Intelligent Software Development, Courtesy of Intelligent Software
The machine learning age is well underway. Today’s software can see novel patterns that humans are unable to see and improve task performance based on experience. Learning algorithms are widely used for varied purposes, including loan approval, intrusion detection, fraud prevention, risk analysis, and online sales optimization. Yet, like the proverbial cobbler who left his children shoeless, software practitioners have been slow to apply the benefits of machine learning to their own work. Join Stephen Frein for a tour of the current machine learning landscape and its most popular tools and techniques, and see how these can be applied to the practice of software development. Through intelligent, machine-driven analysis of existing data sources, we can predict defects, forecast effort, improve design, and streamline testing. Such efforts won’t be push-button easy and will be far from perfect, but they are currently achievable and probably valuable. Best of all, we can start small with a few simple experiments and without the encumbrances that commonly attend “big data” projects. We all want to build software more intelligently, and now intelligent software is in a position to help.
Stephen Frein is a senior director of software engineering at Comcast. He previously managed high profile software projects for the U.S. Department of Defense and the U.S. Treasury. For two decades, he has been leading development and testing teams to questionable success by dint of accidents he cannot reliably replicate. As an adjunct professor at Drexel and Villanova, Stephen delivers soporific lectures on machine learning, database development, and technology management to frequently inattentive students. He has presented at previous TechWell events by sneaking into unused rooms and deceiving the unsuspecting. Stephen enjoys polluting the hive mind via TechBeacon and other industry publications with questionable editorial standards. Visit his poorly maintained vanity website, where he practices writing vapid, self-congratulatory bios.