Prasanth Thangavel

Prasanth | Data Scientist, Technologist, and Innovator

5 min read

Welcome to My Blog (a.k.a. Digital Garden)

Shortcuts (WIP): đź“ŤFeatured linksđź“Ť

timeline
    title Professional Journey
    section Current
        2021-Present : Grab
                     : Senior Data Scientist
                     : ML/DL Systems, Dynamic Pricing
                     : NLP/LLM Solutions, GrabGPT
    section Previous
        2019-2021 : JobShine
                  : Co-founder & CTO
                  : Tech Team Lead
                  : NLP Chatbot & Search Systems
        2019-Present : General Assembly
                  : Lead Instructor
                  : Data Analytics & Data Science
        2017-2022 : NTU
                  : PhD Research Scholar
                  : Detecting Epilesy from EEG using ML
    section Skills & Expertise
        Data Science : Machine Learning
                    : Deep Learning
                    : Signal Processing
        AI Tech     : NLP & LLMs
                    : Transformers & GenAI
                    : Real-time Systems

đź‘‹ Introduction

Hi, I’m Prasanth Thangavel, a Senior Data Scientist with a passion for developing AI-driven solutions for real-time applications. Currently, I enhance user experiences for millions at Grab, Singapore. My expertise spans signal processing, machine learning (ML), deep learning (DL), Natural Language Processing (NLP), and Large Language Models (LLMs). I combine startup leadership and corporate data science experience to drive innovation in dynamic environments. I’m particularly passionate about using advanced AI technologies, especially Generative AI (GenAI), to solve real-world problems.

I find joy 🤗 in analyzing data, building AI/ML models, coding in Python, and sharing my knowledge with others. Recently, I’ve developed interests in NLP, LLMs, Transformers, and Chatbots, and I enjoy experimenting with these technologies both at work and in my spare time.

đź’Ľ Professional Experience

Senior Data Scientist

Mobility at Grab, Singapore (Nov 2021 – Present)

  • Developed and optimized various large-scale ML/DL systems, improving user conversion, engagement, and retention for millions of Grab users across Southeast Asia (SEA).
  • Deployed ML models to reduce cancellations, optimize discounts, and increase ride-sharing adoption.
  • Worked on data analysis and simulations for GrabShare (carpooling), reducing launch preparation effort by 90%.
  • Working on various dynamic pricing strategies, leading to significant BTR/ride conversion and/or revenue increases.
  • DS PIC for productionization of a self-learning NLP/LLM-based solution to predict and prevent harmful cancellations, projected to save millions annually.
  • Conceptualized and developed an early version of GrabGPT, a POC for chat/voice-based interface for passengers using state-of-the-art NLP/LLM models.

Co-founder & CTO

JobShine (JS), Singapore (Jul 2019 – Oct 2021)

  • Built and managed a tech team responsible for the entire tech stack.
  • Developed data-driven strategies, reducing the cost per acquisition of jobseekers.
  • Developed and deployed an NLP-powered chatbot, automating around 80% of job-seeker use-cases.
  • Worked on a Bilateral Search and Recommendation System, reducing job-matching time significantly.
  • Executed cost-effective web-crawling solutions to gather market intelligence.

Lead Instructor, Data Analytics/Data Science

General Assembly (GA), Global (Jul 2019 - Present)

  • Instructed and mentored over 500 professionals, including Fortune 500 clients.
  • Delivered customized training programs with high satisfaction ratings.
  • Developed hands-on teaching methods for big data, ML, and DL.

PhD Research Scholar

Nanyang Technological University (NTU), Singapore (Jul 2017 - Mar 2022)

  • Designed and developed an automated epilepsy diagnosis tool using EEG data.
  • Conducted interdisciplinary research, integrating NLP models for better diagnosis outcomes.
  • Delivered data science and machine learning courses to undergraduate students.

🎓 Education

  • Doctor of Philosophy, Interdisciplinary (Electrical & Electronic Engineering), NTU, Singapore ( 2017-2021)
  • Bachelor’s Degree, Electrical and Electronics Engineering, NTU, Singapore (2013-2016)
  • Diploma, Mechatronics, Robotics, and Automation Engineering, Temasek Polytechnic (2011-2013)

đź“š Publications

  • Peh, W. Y., Prasanth, T., Yao et al. “Six-center assessment of CNN-Transformer with belief matching loss for patient-independent seizure detection in EEG”, IJNS, 2023 Link
  • Prasanth et al. “Improving automated diagnosis of epilepsy from EEGs beyond IEDs”, JNE, 2022 Link
  • Prasanth et al. “Time-frequency decomposition of scalp electroencephalograms improves deep learning based epilepsy diagnosis”, IJNS, 2021 Link
  • J. Thomas, Prasanth T., Peh et al. “Automated adult epilepsy diagnostic tool based on interictal scalp electroencephalogram characteristics: a six-center study”, IJNS, 2021 Link
  • Prasanth et al. “Deep Learning for Interictal Epileptiform Spike Detection from scalp EEG frequency sub bands” in EMBC, 2020 42nd Annual International Conference of the IEEE, 2020 Link
  • J. Thomas, J. Jin, Prasanth T., Elham et al. “Automated Detection of Interictal Epileptiform Discharges from Scalp Electroencephalograms by Convolutional Neural Networks”, IJNS, 2020 Link
  • J.F.A. Ronicko, J. Thomas, Prasanth T. “Diagnostic classification of autism using resting-state fMRI data improves with full correlation functional brain connectivity compared to partial correlation”, JNM, 2020 Link
  • J. Dauwels, J. Thomas, Prasanth T. “Automated Deep Learning based Epilepsy Diagnostic System”, Technology Disclosure accepted at NTUitive, September 2018
  • Improved epileptic spike detection from scalp EEG by cascade of convolutional neural network and shallow classifiers, 8th international workshop on Pattern Recognition and Neuroimaging, Jun 12-14 2018, Singapore [Link]

đź“ś Certifications

  • Deep Learning Specialization from Coursera
  • Using Artificial Intelligence (AI), Machine Learning (ML) in Real Life
  • Building and Deploying Deep Learning Applications with TensorFlow
  • Machine Learning from Coursera by Andrew NG, Stanford University
  • 6.00.1x: Introduction to Computer Science and Programming Using Python, MIT
  • Python Data Structures | Using Databases with Python, University of Michigan

🏅 Honors and Awards

  • PyTorch Scholarship Challenge from Facebook 2018
  • Highly Commended Entrant in Undergraduate Awards 2016
  • ST Electronics Book Price

🤝 Volunteering

Past works

👨🏻‍💻 Explore My Work

Graph View