Lead the launch of accounts recommender / similar companies (2017) using domain specific word2vec (CNN) and model features extracted from corporate descriptions, and news articles including:
- Company specialities/ offerings (harvested via descriptions)
- Company popularity
- Location
- Revenue
- Employee count
- News agents count
- News count
- Co-occurence of companies in 'email watch list'
- Co-occurence of companies in news (heuristics)
