VINOOTHNA.N | AI/ML Dev.

AI Engineer | Machine Learning Developer | Data Scientist | Data Analyst

Delivering AI and Production-Ready Models.

Hi👋🏼! I’m an AI and Machine Learning enthusiast who enjoys turning data into practical, intelligent solutions. With experience in predictive maintenance, cybersecurity automation, and analytics—and a Springer/IEEE-indexed publication. I focus on building models that are accurate, interpretable, and genuinely useful in real-world environments.

View Featured Projects →

Technical Arsenal

Expertise across Programming, Machine Learning, and Data Platforms.

Programming & Data

Python SQL MySQL PySpark Pandas NumPy Data Structures & Algorithms (DSA) Java OOPs

AI & ML / Deep Learning

Scikit-learn XGBoost Data Analysis / EDA Matplotlib / Seaborn TensorFlow / Keras PyTorch Deep Learning Deep Learning (CNN, LSTM, RNN) Explainable AI (XAI) Computer Vision Generative AI (Gen AI) Prompt Engineering NLP (Natural Language Processing)

Tools

Power BI (Interactive Dashboards) APIs Git / GitHub JSON Streamlit (App Development) MongoDB MLFlow

Featured AI/ML Projects

Explainable Hybrid ML for Bearing Fault Classification

Predictive Maintenance | Explainable AI (XAI)

Developed an interpretable predictive maintenance solution that achieved 98.34% accuracy in bearing fault diagnosis. The model utilizes Gradient Boosting on statistical-wavelet features, benchmarked against CNN, LSTM, and RNN Deep Learning models.

  • Methodology: Integrated Wavelet Packet Decomposition for feature extraction.
  • XAI: Used SHAP-based explainability to identify the top contributing vibration features.
  • Recognition: Accepted for publication in Springer LNNS proceedings, indexed in IEEE Xplore.

Cybersecurity Incident Classification (SOC Automation)

XGBoost Optimization | Security Operations

Developed a high-detection accuracy ML model using the Microsoft GUIDE dataset to classify cybersecurity incidents (True Positive, False Positive, Benign). Automated Security Operations Centre (SOC) triage.

  • **Impact:** Reduced SOC incident response time by 30% through automated triage.
  • **Methodology:** Implemented XGBoost optimization, feature engineering, and SMOTE balancing to handle class imbalance.
  • **Stack:** Python, Scikit-learn, XGBoost, imbalanced-learn.

Car-Dekho--used-car-price-prediction

Machine Learning | Price Pridiction

Built a machine learning model & Streamlit app for predicting used car prices with 90% accuracy. Processed 10,000+ data entries, performing Data Cleaning, EDA, and Feature Engineering.

  • **Impact:** 90% accurate prediction of used car prices, enabling more reliable and transparent valuation for buyers and sellers.
  • **Methodology:** Performed extensive data cleaning, exploratory data analysis, and feature engineering on 10,000+ records, and built a supervised ML model deployed via Streamlit.
  • **Stack:** Python, Scikit-learn, matplotlib.pyplot, seaborn, Streamlit.

DataSpark: Market Insights for Global Electronics

Business Intelligence | SQL & Power BI

Performed comprehensive analysis on over 1 million records using SQL and Power BI to uncover critical market trends. This work directly optimized inventory forecasting and enhanced overall data-driven decision-making processes.

  • **Analysis:** Focused on optimizing inventory based on geographical and seasonal market trends.
  • **Tools:** Leveraged **Power BI** to build interactive dashboards for key stakeholders.
  • **Impact:** Optimized inventory forecasting strategy.

Education & Recognition

2024 – Present

MTech - Applied AI

Visvesvaraya National Institute of Technology (VNIT), Nagpur

  • Specialization in Machine Learning Model Development and Deployment.
  • Coursework includes Advanced Deep Learning, Computer Vision, and Generative AI.

2020 – 2024

BTech - Mechanical Engineering

Rajiv Gandhi University of Knowledge Technologies, Basar

  • Foundation in engineering principles, enhanced by deep learning project work.

Key Achievement

Publication Acceptance:

"Explainable Hybrid Gradient Boosting-Deep Learning Framework for Bearing Fault Classification" accepted for publication in **PCEMS International Conference 2025**, to be published in Springer LNNS proceedings and indexed in IEEE Xplore.

Let's Build the Next Generation of AI Solutions

Seeking challenging AI Engineer or Data Scientist roles. I am ready to apply my expertise in AI/ML, Deep Learning, and data pipelining to your team.

vinoothnanadikatla@gmail.com

Find me on professional networks:

Designed & Engineered by Vinoothna Nadikatla.