About

Rakesh Prasanth Achari is a highly skilled Data Scientist with over four years of experience in solving complex problems related to low-resource multi-lingual, audio-video, and fraud detection. Currently working as a Data Scientist-II at Flipkart, he has built diverse machine learning and deep learning models for fraud detection in the e-commerce domain, such as Reseller fraud detection, Buyer return fraud, and Return to origin(RTO), among others. His contributions have saved GMV worth ~10 crores per month and he has also developed a framework to automate retraining of DS models end to end. Rakesh completed his Masters in Machine Learning from the prestigious Indian Institute of Technology, Bombay, where he worked on multimodal video captioning, automatic speech recognition, and published a research paper on Caption Alignment for Low Resource Audio-Visual Data in Interspeech-2020. During his academic tenure, he developed deep learning models in PyTorch and TensorFlow for solving problems in multimodal catering and proposed co-attention driven multimodal models for effective utilization of both audio and video for temporal localization of captions within videos. Rakesh's key strengths include programming in C++, Python, and Java, and working with ML frameworks such as PyTorch and TensorFlow. He is interested in working on next-gen real-world problems and is always open to collaborating with data science enthusiasts. Rakesh's tech stack includes Research Scientist, Data Scientist, ML, Deep Learning, NLP, Python, TensorFlow, PyTorch, Reinforcement Learning, Computer Vision, XGBoost, Neural Networks, Random Forest, Java, Spark, test, SQL, BERT, Sentiment Analysis, Object detection, Decentralized, CNN, OpenCV, Object Detection, Scikit, Kubernetes, Elastic Search, Spring, Search, Azure, Software Engineer, and Apache Hive. Overall, Rakesh is a highly motivated and skilled data scientist who is passionate about solving complex problems and contributing to the field of data science.