Data Scientist
Professional Summary
Data Science leader with 12+ years of experience driving impactful insights and solutions across diverse industries. Proven expertise in building and deploying AI models, data pipelines, and real-time analytics platforms to optimize operations, boost ROI, and empower decision-making. Adept at leveraging cutting-edge technologies like Generative AI, Spark, and NLP to tackle complex challenges in HR, e-commerce, and automotive sectors. Passionate about mentoring and knowledge sharing, fostering a collaborative environment for data-driven success.
Skills
- Programming Languages: Python, MATLAB, C, C#.Net
- Databases: SQL, Google BigQuery
- Frameworks: PySpark, Scikit-Learn, Pytorch, Tensorflow
- Cloud: Microsoft Azure, Google Cloud Platform (GCP)
Experience
Ernst & Young, Gurgaon (Sep 2022 - Present)
- Streamlined HR data analysis by architecting and implementing Azure-based setup and Databricks pipelines, creating an end-to-end automated framework for data-driven decision making. [Demo]
- Utilized Generative AI (GenAI) to tackle complex HR challenges, such as efficiently generating graphs and visualizations for deeper understanding of workforce trends.
- Mentored colleagues on Apache Spark and other relevant tech stacks, empowering them to unlock the potential of data analytics for HR initiatives.
Publicis Sapient, Bengaluru (Jul 2018 - Sep 2022)
- Spearheaded the development of a Spark-powered processing engine for e-commerce data, delivering real-time insights to empower marketers. Implemented cutting-edge image and NLP algorithms to extract critical business metrics.
- Developed an ensemble model with Fbprophet and BQML that boosted booking accuracy by 20%. Deep-dived into COVID’s impact on reservations, providing actionable insights for strategic decision-making. Demo
- Pioneered a Django-based voice assistant system that offered seamless control over news, music, and food orders. Leveraged Dialogflow and other APIs to understand user intent and deliver personalized experiences.
- Maximized marketing ROI by 20% with AI-powered revenue prediction model, optimizing channel allocation based on key performance drivers.
- Utilized computer vision to extract hidden insights from ad creatives, uncovering hidden performance drivers and developing a machine learning model that offered actionable recommendations, maximizing ad campaign effectiveness.
Tata Consultancy Services, Pune (Oct 2011 - Jul 2018)
- Developed and implemented a deep learning-based model using Python and NLTK to categorize user narratives with high accuracy, improving user experience and streamlining operations.
- Leveraged collaborative filtering in Python to recommend triggers for an automotive tool, significantly increasing user efficiency and tool throughput.
- Built a Python-based model that predicts failure time and responsible component using telemetry data, empowering proactive maintenance and cost savings. Additionally, created interactive visualizations with Tableau for clear communication to stakeholders.
- Designed and implemented a MapReduce algorithm in MATLAB to extract and integrate vehicle data from various file formats with DotNet and SQL, achieving a 95% optimization in processing speed. Received Six Sigma Yellow belt certification for the idea.
Education
- M.Tech (VLSI and Embedded systems) from Pune University, India (2014-2016)
- B.Tech (Electronics and TeleCommunication) from Bharati Vidyapeeth University, Pune, India (2007-2011)
- Diploma in Network Security, Bharati Vidyapeeth University (2007)
Certifications
- Generative AI with Large Language Models @Coursera (2024)
- SafeAgilist 5 Certification(2021)
- Apache Spark 3 - Spark Programming in Python @Udemy (2021)
- Apache Airflow, A Real-Time & Hands-on Course on Airflow @Udemy (2020)
- Deep Learning with TensorFlow @Coursera (2019)
Honors and Activities
- Awarded ”Star of the Sprint” for successful delivery and optimizations in 2022.
- Howathon-Runners up in 2020 for developing a voice assistant.
- Expo-Runners up in 2019 for presenting data-driven advertisement using Google Cloud Vision API and ML.
Publications
- “Texture Feature Extraction Methods and Wavelet Standpoint” (International Journal of Innovative Research in Computer and Communication Engineering, 2016)
- “Segmentation based feature extraction of MRI images using Wavelet and its implementation on FPGA” (2016)
Teaching and Mentoring
- Conducted Statistics and Analytics training at Publicis Sapient, GURGAON in 2020.
- Conducted Xilinx Vivado Workshop at DY Patil College of Engg, PUNE in 2016.
References
- Sumil Mehta
- Sr. Marketing Specialist, FRACTAL.AI
- Email: sumilmehta007@gmail.com
- Phone: +(91) 801 008 0189
- Ashish Yadav
- Full Stack Developer, WELLS FARGO
- Email: ashishkumar150190@gmail.com
- Phone: +(91) 784 214 1835
Feel free to reach out for any collaboration or inquiries!