Skip to content
View harshit1531's full-sized avatar
🎯
Focusing
🎯
Focusing

Block or report harshit1531

Block user

Prevent this user from interacting with your repositories and sending you notifications. Learn more about blocking users.

You must be logged in to block users.

Maximum 250 characters. Please don’t include any personal information such as legal names or email addresses. Markdown is supported. This note will only be visible to you.
Report abuse

Contact GitHub support about this user’s behavior. Learn more about reporting abuse.

Report abuse
harshit1531/README.md

Hi 👋, I'm Harshit Mahajan

Process Risk Analyst · Credit Risk & Data Analytics · Python · SQL · Power BI

harshit1531


💫 About Me

🏢 Process Risk Analyst @ Aditya Birla Finance Ltd., Bengaluru — 3 years in NBFC credit risk analytics, MIS reporting, and portfolio monitoring for unsecured lending books.

📊 I turn raw portfolio data into risk decisions — building Python & SQL pipelines that cut manual reporting effort by 40–50%, and Power BI dashboards that give leadership real-time visibility into NPA trends, delinquency movement, and collection efficiency.

🧩 What I work on daily:

  • Roll-forward & vintage analysis · DPD bucket tracking · Stage 1/2/3 monitoring under IND AS 109
  • NPA/GNPA reports · SMA 0/1/2 classification · Slippage & cure rate analysis
  • ECL modelling inputs (PD / LGD / EAD) · Early warning signal (EWS) frameworks
  • MIS dashboards in Power BI (DAX) · Advanced Excel models · Management decks for senior leadership

🌱 Currently deepening: Predictive risk modelling · Scorecard development · Data engineering for scalable reporting infrastructure

🤝 Open to collaborate on: Risk analytics · Credit analytics · BFSI data projects · Financial data storytelling · Python automation for reporting


🌐 Connect With Me

LinkedIn Instagram Stack Overflow


💻 Tech Stack

Programming & Data

Python MySQL Pandas NumPy scikit-learn SciPy

BI & Visualisation

Power Bi Tableau Microsoft Excel Matplotlib Seaborn

Tools & Environment

Anaconda Jupyter Notebook VS Code


🗂️ Featured Projects

Python · Scikit-learn · Pandas · Tableau

Built logistic regression and decision tree classifiers achieving 78%+ accuracy. Applied SMOTE to handle class imbalance and designed an interactive Tableau dashboard segmenting patients by risk tier to support clinical prioritisation.


Python · Seaborn · Tableau · Excel

Analysed 1,000+ service records to engineer KPIs for closure rate, escalation frequency, and service delays — surfacing CX performance gaps through interactive dashboards.


📊 GitHub Stats




🏆 GitHub Trophies


🎓 Certifications

  • 📜 Data Science with Python — Simplilearn
  • 📜 Machine Learning Advanced — Simplilearn
  • 📜 Tableau Desktop Specialist — Simplilearn
  • 📜 SQL & Business Analytics with Excel — Simplilearn
  • 📜 Python Programming — ICT Academy, IIT Kanpur

✍️ Random Dev Quote


"Good risk management starts with visibility — knowing what's moving, why it's moving, and how fast."

Pinned Loading

  1. Healthcare-Predicting-Diabetes-A-Data-Driven-Approach-to-Understanding-and-Treating-Chronic-Diseases Healthcare-Predicting-Diabetes-A-Data-Driven-Approach-to-Understanding-and-Treating-Chronic-Diseases Public

    This project aimed to predict whether or not a patient had diabetes using data from the National Institute of Diabetes and Digestive and Kidney Diseases (NIDDK). The dataset included various medica…

    Jupyter Notebook

  2. Movielens-Case-Study Movielens-Case-Study Public

    Performed analysis using Exploratory Data Analysis technique.Found features affecting the ratings of any particular movie and build a model to predict the movie ratings.

    Jupyter Notebook

  3. Mercedes-Benz-Greener-Manufacturing Mercedes-Benz-Greener-Manufacturing Public

    Reduce the time that cars spend on the test bench. Work with a dataset representing different permutations of features in a Mercedes-Benz car to predict the time it takes to pass testing. Optimal a…

    Jupyter Notebook

  4. Comcast-Telecom-Consumer-Complaints-Analysis Comcast-Telecom-Consumer-Complaints-Analysis Public

    This project was completed as a part of assessment for Data Science with Python module. We used different Python libraries such as NumPy, SciPy, Pandas, scikit-learn and matplotlib to complete the …

    Jupyter Notebook

  5. Customer-Service-Requests-Analysis. Customer-Service-Requests-Analysis. Public

    Perform data analysis of service request (311) calls from New York City. I have utilized data wrangling techniques to understand the pattern in the data and visualize the major types of complaints.

    Jupyter Notebook

  6. Web-Scrapping-API Web-Scrapping-API Public

    Jupyter Notebook