KOUSHIK HARIDASYAM

Took the responsibility of understanding and developing the Salary Transaction Identification mechanism currently in place. Developed a fuzzy string matching technique to identify the company that is providing the salary. Using the DBSCAN algorithm, able to determine a salaried employee’s bonus. In order to give real-time insights into the product, marketing funnels, and business KPIs, data and reporting architecture was built entirely from the ground up using SQL and Power-BI. Building a Voice bot which answers customers questions. For Understanding user queries and generating responses, employing various NLP techniques such as intent recognition, named entity recognition (NER), and sentiment analysis. Trained 4 direct reportees in fixing issues and project deliverables.

Worked on Big Data scratch project to add credit report behavior in the Experian Brazil bureau. Proactively provided support during the UAT phase. The project is to build an ETL (Extract, Transform, Load) pipeline for credit score calculation. Spark and Scala were majorly used to create the engine to drive this application. Developed a spark application which Analyzed the QA differences to extract related sample data to recreate the bug, which was found during the QA, the tool was later integrated with the QA engine as a configurable functionality.

Worked at Engine Development Centre. Goal of the project was to research if the temperature sensors of the exhaust system were required or not.