Aditya Sharma

Utilized essential data science libraries, including sklearn, numpy, pandas, Plotly, etc., to build regression models and implement Ensemble learning techniques such as Decision Tree and Random Forest, resulting in an average accuracy improvement of 15% for predictive models. Demonstrated expertise in classification models, including Logistic Regression, SVM, Naive Bayes, and KNN effectively applying them to address various data-driven challenges resulting in a 20% reduction in misclassification errors. Implemented k-means, Agglomerative clustering, and PCA in customer segmentation, resulting in a 30% engagement upsurge. Proficient in time series analysis: skilled in ARIMA, SARIMA, and Prophet models for precise trend spotting and forecasting. Built Python-based Amazon web scraper (Beautiful Soup, Selenium) showcasing web scraping, data extraction, and automation skills. Performed sentiment analysis using custom SVM, Random Forest, and Logistic Regression models, trained on one dataset, tested on scraped data.

Primary responsibilities included conducting research, experimenting with AI algorithms, and developing solutions that apply AI techniques to solve real-world problems. Used TensorFlow, Keras, NumPy, Pandas, Seaborn and, Matplotlib.