Vyom Shrivastava

Data Scientist IV at Credit Karma
  • Claim this Profile
Contact Information
us****@****om
(386) 825-5501
Location
Los Angeles Metropolitan Area
Languages
  • English Full professional proficiency
  • Hindi Native or bilingual proficiency

Topline Score

Topline score feature will be out soon.

Bio

Generated by
Topline AI

5.0

/5.0
/ Based on 2 ratings
  • (2)
  • (0)
  • (0)
  • (0)
  • (0)

Filter reviews by:

Biao "Bill" Chang, Ph.D.

I was Vyom's direct manager for 14 months and enjoyed every minute working together! Vyom was about 2 years after graduation from his master's when we started working together, and I was immediately impressed by his level of professional maturity in machine learning applications: he almost single-handedly created an end-to-end ML training/serving pipeline for ATO detection/mitigation. Vyom is also a quick learner: he learned about a technically complex ML training/serving platform in a month and was able to push new features/models into prod successfully afterwards. He is very hardworking and at the same time really easy to work with; this combination makes him well respected by junior and senior members on the team. Because of all these qualifications and achievements, I promoted Vyom to the next level within half a year working together, and I would recommend him to any ML-related role without reservation!

Dan Anderson

Vyom is a highly intelligent data Jedi with excellent listening skills and exceptional diligence at completing the task/getting the job done. His technical skills are top notch and his ability to understand the data structure and problem statement and then find the proper tool for the job is best in class. He’s professional, kind, courteous, patient, tactful and insightful, yet isn’t afraid to offer counter advice or alternative ideas that might not be popular or expected but that are the right thing to do in the situation. Not only is he a bright individual, but his curiosity and introspection about the world around him creates a natural learning environment for him daily, constantly augmenting his knowledge, skills and abilities on the job. His best-practice recommendations are nicely paired both technically (hands-on how-to) and academically (consultative). He works well both in a team and an individual environment and he brings a great deal of customer support with his people skills and listening/comprehension ability. He documents his work in a detailed fashion, can describe it in non-technical ways to an average business user and he’s always willing to help or go the extra mile to ensure that everyone understands technical goals, capabilities, limitations or other technical project-oriented topics. He’d make a great addition to a technical team or as an individual SME deployed to a client site solving complex, data-driven problems and developing effective and efficient solutions.

You need to have a working account to view this content.
You need to have a working account to view this content.

Credentials

  • Machine Learning on Google Cloud Specialization
    Coursera
    Mar, 2023
    - Nov, 2024
  • Deploying Scalable Machine Learning for Data Science
    LinkedIn
    Jan, 2020
    - Nov, 2024
  • Learning Docker
    LinkedIn
    Dec, 2019
    - Nov, 2024
  • R Programming
    Coursera
    Jun, 2017
    - Nov, 2024

Experience

    • United States
    • Consumer Services
    • 700 & Above Employee
    • Data Scientist IV
      • Mar 2022 - Present

      - Developed Generic Account Risk Model to assign risk scores to members to decide ACH Money Hold times, Overdraft limit decisioning and Mobile check deposit risk. - Built Customer Intent Recognition & Churn Predictions models for customer acquisition and retention.- Created Supervised ML models to predict Account Takeovers, Account Sharing & Identity Theft. - Developed model to detect ACH transaction fraud in real-time. - Created models to identify risky new accounts trying to register/upgrade to financial products.- Built Unsupervised Anomaly Detection models like Autoencoders and Isolation forest to identify anomalous logins, registrations and transactions.- Developed a community detection model to identify fraud rings and linked accounts.- Analyzed large scale data to identify anomalies, fraudulent activities and associated fraud.- Analyze recent fraud patterns and create rules to penalize suspicious activities.- Created a real-time alerting system to monitor user activities and alert on increased suspicious activities.- Created visualisation and dashboards to monitor model performance on Looker, Google Data Studio and Dash- Designed workflow pipelines to generate features, train model, predict and produce analysis report on Airflow Show less

    • Data Scientist II, Trust & Safety
      • Dec 2020 - Mar 2022

    • Data Scientist, Trust & Safety
      • Feb 2019 - Dec 2020

      - Create Supervised and Unsupervised Machine Learning models to predict Transaction Fraud, Account Takeovers, Account Sharing & Identity Theft. - Analyze large scale data to identify anomalies, fraudulent activities and associated fraud.- Analyze recent fraud patterns and create rules to penalize suspicious activities.- Create a near real-time alerting system to monitor user activities and alert on increased suspicious activities.- Created Visualisations and dashboards to monitor model performances on Looker and Google Data Studio- Deployed model workflow pipelines on Airflow Show less

    • United States
    • Higher Education
    • 300 - 400 Employee
    • Course Instructor
      • Aug 2018 - Dec 2018

      Instructor for the course Introduction to Programming (JAVA) Instructor for the course Introduction to Programming (JAVA)

    • United States
    • IT Services and IT Consulting
    • 1 - 100 Employee
    • Data Scientist
      • May 2018 - Dec 2018

      – Created a model that summarizes the past performance of the MLB League players and learns from their past Fantasy League stats to predict the points they will earn in the next game. Using Apache Spark, Python. – Created a model that predicts the ownership of each player (Number of participants who will select a specific player for their lineup for a Fantasy League Tournament) Using Python, Pandas, Scikit-learn. – Created a model that summarizes the past performance of the MLB League players and learns from their past Fantasy League stats to predict the points they will earn in the next game. Using Apache Spark, Python. – Created a model that predicts the ownership of each player (Number of participants who will select a specific player for their lineup for a Fantasy League Tournament) Using Python, Pandas, Scikit-learn.

    • United States
    • Higher Education
    • 100 - 200 Employee
    • Graduate Research Assistant
      • Aug 2017 - May 2018

      Analyze eye movement data of Primary grade students to study their reading patterns. Analyze eye movement data of Primary grade students to study their reading patterns.

    • United States
    • Higher Education
    • 300 - 400 Employee
    • Graduate Teaching Assistant
      • Jan 2017 - May 2018

      Teach in labs for course "CSCI 1301: Introduction to Programming (JAVA)" Teach in labs for course "CSCI 1301: Introduction to Programming (JAVA)"

Education

  • University of Georgia - Franklin College of Arts and Sciences
    Master of Science (M.S.), Computer Science
    2016 - 2018
  • University Institute of Technology, RGPV
    Bachelor of Engineering (B.E.), Computer Science
    2012 - 2016

Community

You need to have a working account to view this content. Click here to join now