Data Science with less than a year in Machine Learning & NLP
AI is analyzing your overall score…
Identifying your key strengths…
Evaluating your skill match against the job requirements…
Assessing your cultural and operational fit
Data scientist with a track record of measurable results: 18% RMSE reduction in financial time-series forecasting, 22% precision gain in a production-scale recommendation engine, and 87% NLP classification accuracy using fine-tuned DistilBERT. Builds complete data science pipelines - SQL extraction, EDA, model development, evaluation, and Streamlit deployment. Proficient in Python, SQL, Scikit-learn, TensorFlow, and PyTorch. Targeting an entry-level Data Scientist role.
KLE College of Engineering & Technology, Chikodi
B.E. · Artificial Intelligence & Data Science
August 1, 2022 – June 30, 2026
Prinston Smart Engineers
Data Science Intern
February 1, 2026 – May 31, 2026
India
Hybrid Recommendation Engine
June 20, 2026 – Present
Solved the two core recommender failure modes simultaneously - cold-start (handled via content-based fallback) and sparse matrix (via weighted ensemble blending) - on the MovieLens 1M dataset (1M+ ratings, 6K users, 4K movies); engineered user preference and item feature vectors from SQL-extracted interaction data. 22% improvement in precision@10 over single-method baselines; sub-200ms response time across 100K+ users and 50K+ items — personalized recommendations demonstrably more relevant than either standalone approach.
View ProjectTime Series Forecasting for Stock Market
June 20, 2026 – Present
Compared 3 forecasting architectures (LSTM deep learning, Facebook Prophet additive, ARIMA statistical) on 5 years of daily OHLCV data from 10 S&P 500 stocks via SQL + yfinance; engineered lag features, rolling mean/std statistics, and seasonal decomposition indicators to capture non-linear temporal dependencies. LSTM outperformed Prophet by 18% on RMSE with 62% directional accuracy on held-out data — delivered a 30-day interactive Streamlit forecasting dashboard with model comparison charts and real-time refresh.
View ProjectSentiment Analysis Pipeline with Real-Time Dashboard
June 20, 2026 – Present
Built a complete 3-class NLP pipeline (Positive/Neutral/Negative) on 50,000+ customer reviews: SQL extraction → text normalization → TF-IDF vectorization → DistilBERT fine-tuning → multi-classifier benchmark (Logistic Regression, SVM, Naive Bayes, Transformers); deployed real-time Streamlit dashboard with dynamic filters, trend charts, and CSV export. Fine-tuned DistilBERT hit 87% accuracy — 14 percentage points above TF-IDF baseline; dashboard processes 1000+ reviews per batch and replaced 40+ hours of weekly manual analysis, cutting insight turnaround from days to minutes.
View ProjectMachine Learning Specialization
Coursera
June 1, 2026 – Present
Data Science & Generative AI
Besant Technologies
June 1, 2026 – Present
AI Fundamentals
IBM
June 1, 2026 – Present
PyTorch for Deep Learning
Scaler
June 1, 2026 – Present
Python for Data Analysis: Pandas & NumPy
Coursera
June 1, 2026 – Present
Cultural Fit Analysis
The candidate's project diversity (recommendation engines, time series forecasting, sentiment analysis) and breadth of technical skills (ML, DL, NLP, MLOps tools like Streamlit, GCP) indicate a strong interest in various data science applications. The target role 'Memora Founding Engineer' suggests a need for versatility and a proactive approach, which aligns with the candidate's demonstrated initiative in personal projects. The candidate is currently pursuing a B.E. in AI & Data Science, with an expected graduation in 2026, indicating a strong academic foundation and a continuous learning mindset. However, the experience level is very low (0 years post-graduation), which might be a mismatch for a 'Founding Engineer' role that typically requires significant industry experience.
Soft Skills & Operational Fit
The candidate lists 'Adaptability & Flexibility', 'Collaboration & Team Work', and 'Time Management' as soft skills. The internship experience mentions collaboration in an agile team and ensuring scalable, efficient model performance within sprint deadlines, which aligns with operational fit for a fast-paced engineering role. However, without direct assessment, these are self-reported.