About

Kunal Sawant is a skilled and experienced Data Scientist with a background in application development and financial services. He is proficient in Python, SQL, Java, C, and C++, and has strong knowledge of libraries such as pandas, numpy, and sklearn. Kunal holds a Bachelor's Degree in Information Technology from Sardar Patel Institute of Technology. Currently, Kunal is working as a Senior Machine Learning Engineer at Servify, where he has developed a fraud detection pre-purchase model using XGboost Classifier and scikit-learn. He has also designed an API using Flask to interpret the model using SHAP library, which provides insight into which features had more impact while deciding whether something is fraud or not. In his previous role as a Machine Learning Engineer at Servify, Kunal created a service centre cost forecasting and risk assessment model using an Ensemble of various models. He also provided business teams with EDA on High Risk service centres from historical data and developed an API using Django and libraries like fuzzywuzzy to identify whether the phone given by the customer is an original phone or a fake phone. Prior to joining Servify, Kunal worked as an Associate at JP Morgan, where he developed an application that helps users to collect data from multiple data sources like excel, SQL databases, scraping emails, and excels. He also improved the throughput of the application by 90% using a distributed compute system named Compute BackBone and DAG Framework named DG2. Kunal has a diverse tech stack that includes ML, SQL, Python, Scikit, XGBoost, Pandas, Computer Vision, NLP, TensorFlow, Flask, Java, Docker, Keras, AWS, Django, Spark, Big Data, test, Redis, MySQL, Microservices, ETL, and Web. With 6.86 years of relevant experience, Kunal is a strong problem solver and a skilled researcher who is capable of delivering impactful solutions.