Ashok Krishna

Ashok Krishna-|-|Plot No. 7, Color Homes F1, Kandanchavadi, Perungudi, Chennai-96. Data Scientist, currently working as the head of the Data Science team at Unmetric with 3+ years of experience in identifying, building and managing various Machine Learning projects. Education- - B.Tech in Instrumentation Engineering, IIT Kharagpur - Complemented a B.Tech Project which focuses on Distribution Network Reconfiguration to reduce Power Loss and Voltage Deviation using Hybrid Evolutionary Algorithm (ACO-SA) and Artificial Neural Networks. - Competed in various Machine Learning Competitions. In one such competition, TNT – The Number Thing (LatentView) achieved 15th position all over India out of 1100 teams and 1st from IIT Kharagpur. Board of Intermediate Education in Sri Chaitanya Junior College Professional Experience Data Scientist (Product), Unmetric Technologies Pvt. Inc, Chennai, Tamil Nadu • Product Management o Overseen many of the projects mentioned below (Image Analytics, Automated Campaign Detection, Word Cloud) right from conceptualization stage till they were pushed to Production. • Promoted Post Detection o Built a Random Forest model with a 96% accuracy (F1 score of 0.92) which predicts if a Facebook Post was promoted or organic using the Interactions Data (Likes, Comments, Shares) of a post. • Reach & Impressions o Modelled the complex performance of a Facebook Post to predict its Reach. Improved the model performance from an Error Rate of 37%(𝑣𝑒𝑟𝑠𝑖𝑜𝑛 1) to 9%(𝑣𝑒𝑟𝑠𝑖𝑜𝑛 3). • Text Analytics o Trending Hashtags – Developed an algorithm which takes brand tweets and mentioned tweets to find trending hashtags brands are jumping on daily using Chi-Squared Test. o Word Cloud – Developed a sophisticated algorithm which extracts important information like noun phrases, hashtags, emojis. • Image Analytics API o Object Detection – Used TensorFlow’s pre-trained Object Detection Model (Faster R-CNN Inception Resnet) for out-of-the-box inference. o Dominant Color Detection – Developed an algorithm which outputs the Dominant Colors in an Image. • Automated Campaign Finder o Developed a methodology to automate a slow and unscalable process of finding Social Media Campaigns run by Brands. This job was done previously by a team of 5. • Data Analysis o Collected user interaction data from various sources (Mixpanel, Database, Google Analytics etc…), automated analysis pipelines, constructed KPIs, and designed and automated dashboards to measure a product/feature success. Certifications • Machine Learning Engineer Nanodegree – Udacity • Deep Learning Specialization – Coursera taught by Dr. Andrew Ng Skills • Machine Learning, R, Python, MySQL, Supervised Learning, Unsupervised Learning, Reinforcement Learning, Deep Learning, Java Script, Excel. Extracurricular Activities • Endurance Runner – Completed two Half-Marathons with a personal best of 2 hours 7 minutes. • Photography • Sports: Table Tennis and Badminton.