About

Humeil Makhija is a skilled and well-qualified Data Scientist with over 2 years of experience in breaking down large data sets, gathering relevant points, and solving advanced business problems. He is a passionate nerd turned Data Scientist who is skilled in statistical modelling, ML, NLP, and AddTech industry. Currently working as a Data Scientist at zeotap, Humeil has generated $2M revenue by optimizing Billion scale user identity graph, increasing matched output id's to be exported, and reducing depth and density of the same at the same time. Humeil has reduced traversal time exponentially by devising community detection algorithms over the billion scale graph. He has achieved 3-5X output exported cookies over resolved graph by traversing 4-5 levels from input matched emails id'ss from clients in their graph. Humeil has saved 2-3 Days of manual labour work per week by delivering an end-to-end reporting pipeline in pyspark that builds complete stats on the resolved identity graph to the engineering teams in just a few hours. He has built 4+ ETL pipelines using pyspark, Hadoop, Airflow, and ML algorithms to process Petabyte scale 3rd party data including demographics, psychographics, preferences, and purchase data from multiple data partners. Humeil has also orchestrated Clustering, Anomaly detection, and Scoring algorithms on their optimized identity graph to correctly link multiple and conflicting data elements to ensure that consumer identities can be correctly resolved. He has previously worked as a Data Science Intern at zeotap where he automated end-to-end ML pipelines to optimize storage and computation cost of their Billion scale Profile Store data giving better performance affecting the segment volume export for a campaign largely as compared to most of the industry standard TTL based models. Humeil has also published a paper in ADKDD 2021 on the above-mentioned work. He has also worked as a Software Developer Internship at Strand Life Sciences. Humeil holds a Bachelor of Technology degree in Computer Science from BIT Mesra. He is proficient in various technologies such as Data Scientist, Research Scientist, ML, NLP, Apache Airflow, Hadoop, ETL, Spark, Recommendation system, Software Engineer, Python, Scikit, test, Pandas, MySQL, Search, Pytorch, GCP, Django, and Java. With 3.86 years of relevant experience, Humeil is a skilled and passionate Data