I'm a data scientist with a strong Natural Language Processing, predictive modeling, forecasting, and statistical analysis background. With experience using Python (and libraries), Excel, SQL, and Power BI, I have a proven track record of transforming complex data into valuable insights that drive business decisions. My passion lies in uncovering patterns and trends that help organizations gain a competitive edge in their respective industries. Below is a high-level summary of my proficiency. ------------------------------------------------------------------------------------------------------------------- • Programming: Python (Numpy, Pandas, spaCy, SciPy, Sklearn, Statsmodels, NLTK, TensorFlow, Keras, PyTorch, HuggingFace Transformers, PyMC3, etc.), SQL, R. • Statistics: Experimental Design, Hypothesis Testing (A/B Testing), Inferential Statistics, Regression Analysis. • Experience using Machine Learning techniques: SVM, XGBoost, RandomForest, Bayesian Gaussian Mixture Model, KNN Classifier, K-Means Clustering, Logistic Regression, SHAP, etc. • Experience using Deep Learning techniques: Shallow Networks, Deep Neural Networks, LSTM, CNN, Autoencoders, and Transformers. • Experience in NLP: Text Summarization, Text Classification, Sentiment Analysis, Named Entity Recognition, Synthetic Data Generation, Language Translation, Sentence Analysis, etc. • Data Visualization: Tableau, Power BI, Using Python libraries Matplotlib, Seaborn, Bokeh, Plotly ------------------------------------------------------------------------------------------------------------------- My Github profile: github.com/pradeepsaminathan My Blog: https://dataandtech.blogspot.com/ ------------------------------------------------------------------------------------------------------------------- Reach me at: pradeepo@buffalo.edu