Puneet Chandna

Puneet Chandna

About

Detail

Consultant - Analytics at Absolutdata
Haryana, India

Timeline


work
Job
school
Education
folder
Project
auto_stories
Publication

Résumé


Jobs verified_user 0% verified
  • A
    Consultant - Analytics
    Absolutdata Analyticsan Infogain company
    May 2022 - Current (4 years)
    • Extracted specific details from insurance claim documents using a mix of open source (Openllama, Falcon, Mpt, Xgen) and paid LLMs (GPT-3.5, GPT-3.5-turbo). Utilized model libraries like Exllama and Autogptq, and experimented with embedding models such as Instructor large and text-embedding-ada-002 for RAG. Demonstrated results using Langchain and Llamaindex frameworks. • Developed a pipeline to classify whether an insurance claim would be overridden to be sent to an insurance adjuster or not. • Classified safety incidents on aircraft using Longformer in a multi-label multi-level hierarchical text classification setting for 1800 labels. Achieved over 98% recall across all models/levels, exceeding client expectations.
  • SecomindAI India
    Data Scientist
    SecomindAI India
    Nov 2021 - May 2022 (7 months)
    • Collaborated with a smart building solutions provider to address challenges in the time series module of smart IoT windows. Developed innovative solutions utilizing a photochromatic layer and multiple sensors to adjust window tint based on external weather conditions. Engineered custom time series forecasting models combining NLP and time series concepts for multivariate multi-step time series forecasting.
  • 47 Degrees
    Machine Learning Engineer
    47 Degrees
    Feb 2021 - Sep 2021 (8 months)
    • Worked with various image processing and object detection techniques to create smart grocery shelves and coolers to detect out of stock inventory. Created a model with 99% map, which was a huge improvement over the existing model which struggled with detecting hanging shelves and high latency. • Worked with various image processing and object detection techniques to detect slaughtered and alive chickens in a meat processing plant. Acknowledged the challenges and suggested improvements to the client for a minimum viable product.
  • Infosys
    Senior Systems Engineer
    Infosys
    Jul 2020 - Feb 2021 (8 months)
    • Worked as a developer in the analytics division for various clients creating POCs and discovering areas for value addition. • Worked on a project for an international telecom operator to predict customer churn behavior. • Worked on a project to segment customers into different clusters for effective marketing. • Worked on a project to forecast sales for an international retailer. • Gathering various pain points and requirements from all teams for automation purposes. • Scraping, cleaning and analyzing large datasets and performing EDA for model building.
  • Applied AI Course
    Student
    Applied AI Course
    Dec 2019 - Oct 2020 (11 months)
    Successfully completed the rigorous 1 year course covering python fundamentals, SQL, Algebra, Probability and Statistics, Dimensionality reduction, Supervised ML techniques, Decision Trees, Bagging and Boosting, Unsupervised learning/Clustering, Recommender Systems and Matrix Factorization, Neural Networks, Computer Vision and NLP. 30 Practical assessments with 13+ end-to-end case studies, 2 self-made case studies and 2 self-written blogs based on real-world business problems.
  • Infosys
    Systems Engineer
    Infosys
    Jun 2018 - Jul 2020 (2 years 2 months)
    • Worked as a developer in the analytics division for various clients creating POCs and discovering areas for value addition. • Worked on a project for an international telecom operator to predict customer churn behavior. • Worked on a project to segment customers into different clusters for effective marketing. • Worked on a project to forecast sales for an international retailer. • Gathering various pain points and requirements from all teams for automation purposes. • Scraping, cleaning and analyzing large datasets and performing EDA for model building.
Education verified_user 0% verified
  • Applied AI Course
    Applied AI Course
    Applied AI Course
    Dec 2020
  • D
    Convolutional Neural Networks
    DeepLearningAI
    Dec 2020
  • Guru Gobind Singh Indraprastha University
    Bachelor of Technology, Computer Science
    Guru Gobind Singh Indraprastha University
    Jan 2014 - Dec 2018 (5 years)
Projects (professional or personal) verified_user 0% verified
  • M
    Multivariate multi-step time series forecasting using sequence models
    Jan 2022 - Mar 2023 (1 year 3 months)
    Multivariate multi-step time series forecasting using sequence models
  • R
    Real Image Denoising with Feature Attention (RIDNet)
    Sep 2020 - Oct 2020 (2 months)
    One of the fundamental challenges in the field of image processing and computer vision is image denoising, where the underlying goal is to estimate the original image by suppressing noise from a noise-contaminated version of the image.
Publications verified_user 0% verified
  • m
    Multivariate multi-step time series forecasting using sequence models (4/4)
    mediumcom
    Mar 2023
    Multivariate multi-step time series forecasting using sequence models
  • m
    Multivariate multi-step time series forecasting using sequence models (3/4)
    mediumcom
    Mar 2023
    Multivariate multi-step time series forecasting using sequence models