Kavya Negi

• Developing an NLP-powered resume screening tool leveraging TextBlob and machine learning to extract, analyze, and rank candidate profiles based on job relevance.
• Automated keyword matching, sentiment analysis, and scoring to streamline the recruitment process and improve candidate-job fit.

https://docs.google.com/document/d/1xTf6wbcbhJcKEtp9OicXmbsos73wwgmNsYJtG4hZ148/edit?usp=sharing

• Built a churn prediction model with 97% accuracy using Logistic Regression, applying feature engineering and data preprocessing techniques
• Implemented data visualization techniques to effectively communicate insights to stakeholders.
• Identified, analyzed and interpreted trends in complex data sets using supervised and unsupervised learning techniques.

https://github.com/Kavyanegi0007/Customer-Churn-Report-and-Prediction

• Developed and deployed advanced RAG system for reading multiple documents
• Drug Discovery of PROTACS targeting CDK9 using Machine Learning and Cheminformatics
• Applied PCA, KMeans, and kNN with SMILES-based similarity to cluster CDK9-targeting compounds and identify potent analogs.
• Leveraged RDKit for structural parsing and uncovered 5 promising compounds, showcasing data science in oncology drug design.
• Synthetic Time Series Data Generator and Anomaly Detection System with Performance Optimization
• Simulated realistic time series data with seasonal patterns, trends, and configurable noise; injected local and pattern-based anomalies to mimic real-world scenarios.
• Performed advanced statistical analysis (mean, variance, skewness, kurtosis) and optimized memory usage with a sliding window mechanism.
• Implemented and benchmarked classic sorting and searching algorithms in Python to compare their performance across various input sizes.

https://github.com/Kavyanegi0007/Drug-discovery-using-KNN-Clusters

https://github.com/Kavyanegi0007/PDF-Text-Extractor

https://github.com/Kavyanegi0007/real-time-anomaly-detection-system

https://github.com/Kavyanegi0007/benchmark-algorithms/blob/main/benchmark.py

• Tracked 1500+ monthly website visits and analyzed trends using statistical techniques and advanced excel spreadsheet functions
• Streamlined reporting processes, resulting in faster turnaround times for monthly performance reports.
• Utilized data visualization tools to effectively communicate business insights and identified 10+ KPIs using Python (Pandas, Matplotlib, Seaborn)

• Developed an NLP pipeline using spaCy and TextBlob for keyword extraction and sentiment analysis on reviews of more than 100 products
• Created sentiment-based content driving sales by 18% in under 6 months

https://github.com/Kavyanegi0007/Product-sentiment-analysis-and-keyword-insights