About

Shanya Anand is a highly skilled Senior Data Scientist with a background in Engineering Physics from the Indian Institute of Technology, Bombay. With almost three years of relevant experience, Shanya has a proven track record of delivering innovative solutions to complex data problems. Currently, Shanya is working at Publicis Sapient, where she has developed a controllable language generation model for description generation, using a pre-trained GPT-2 and simple attributes to guide text generation. She has also developed a model for classifying flora species using one-shot classification and elastic search. Additionally, Shanya has programmed a model to validate web page accessibility standards using object detection with a text detection module. Prior to her current position, Shanya worked at Siemens, where she built an integrated UI to classify bugs in software, incorporating a Random Forest Model. She improved the F1 score of the model through SMOTE, TOMEK, and Cost Sensitive techniques. Shanya also worked on a project to predict the number of defects using a Transformer Attention Model, which increased performance metrics by approximately 60 percent. Shanya's past experience also includes working at Homi Bhabha Centre for Science Education, where she built an algorithm to quickly reconstruct particle tracks from 3D points left in silicon detectors using a Siamese DNN. Shanya is proficient in a wide range of technologies, including GPT, Random Forest, Elastic Search, Neural Networks, AWS, Java, SQL, Pytorch, Tensorflow, Flask, and Docker, among others. She is a skilled researcher, data scientist, and software engineer with expertise in object detection, image segmentation, and deep learning. Shanya is a team player who enjoys discussing ideas and deploying agile solutions on a short time scale. She is passionate about contributing to start-ups and is always eager to take on new challenges.