Jay M. Patel

Jay M. Patel is a software developer with over 10 years experience in data mining, web crawling/scraping, machine learning and natural language processing (NLP) projects. He is a co-founder and principal data scientist of Specrom Analytics (http://www.specrom.com ) providing content, email, social marketing and social listening products and services using web crawling/scraping and advanced text mining. Jay worked at the US Environmental Protection Agency (EPA) for five years where he designed workflows to crawl and extract useful insights from hundreds of thousands of documents that were parts of regulatory filings from companies. He also led one of the first research teams within the agency to use Apache Spark-based workflows for chem and bioinformatics applications such as chemical similarities and quantitative structure activity relationships. He developed recurrent neural networks and more advanced LSTM models in Tensorflow for chemical SMILES generation. Jay graduated with a bachelors degree in engineering from Institute of chemical technology, University of Mumbai, India and M.S. in Chemistry from University of Georgia, Athens, GA, USA. Jay serves as an editor at a medium publication called Web Data Extraction (https://medium.com/web-data-extraction) and also blogs about personal projects, open source packages and experiences as a startup founder on his personal site (http://jaympatel.com ).