Sharath Urs P

Sharath is a professional analyst with over 3.5 years of experience in the field of data analytics and statistical modeling and 3 years if experience in KPO Sector. He is adept at using Python for creating machine learning, visualization, and insight generation for generating business value. Sharath has worked on data science projects in the CPG, and Finance industries, and has extensive experience in market mix modeling. He holds a master's degree in the field of Statistics.

• Market Mix Modeling -

Managed Market Mix Modeling projects for three regions. Analyzed complex datasets to extract actionable insights and drive strategic decision-making. Assessed and optimized marketing strategies by modeling the impact of various marketing tactics on sales. Leveraged statistical techniques and machine learning algorithms to provide actionable insights for marketing decision-making. Proficient in Python, Excel, Linear Regression, Statsmodels, and Scikit Learn.

• Credit card fraud detection -

Conducted comprehensive exploratory data analysis (EDA) on transaction data to unveil underlying patterns and anomalies. Utilized various visualization techniques such as histograms, box plots, and scatter plots to gain insights into data distribution and relationships. Employed statistical tests and hypothesis testing to assess feature significance and detect potential fraud patterns. Leveraged EDA findings to inform feature engineering and model development for credit card fraud detection. Built an end-to-end pipeline integrating EDA, feature engineering, and model training to enhance fraud detection capabilities.

• Credit Risk Modeling -

Developed machine learning models for Credit Risk Modeling to predict loan repayment probabilities. Utilized Python programming, with a strong emphasis on exploratory data analysis (EDA) techniques. Conducted extensive exploratory data analysis to identify key patterns and trends in the dataset. Employed advanced feature engineering techniques to extract meaningful information from the data. Applied up-sampling techniques to address imbalanced classes in the dataset. Utilized a variety of machine learning algorithms and feature selection methods to optimize model performance. Analyzed feature importance to gain valuable insights into the factors affecting loan repayment probabilities.

• Problem solving
• Cross-functional work
• Agile