Raghav Khemka

Experienced Data Scientist with expertise in compiling, transforming, and analyzing complex information using advanced software. Proficient in machine learning and deep learning techniques and adept at managing large datasets. Highly skilled in gathering, cleaning, and organizing data for usability by both technical and non-technical personnel. Effective communicator able to convey insights clearly to stakeholders, fostering consensus around well-founded models.

• Developed a machine learning model using Logistic Regression and Random Forest to rank and prioritize 6,000 prospects by their likelihood to purchase. Integrated diverse data sources like Capital IQ Pro, leveraging features such as industry trends, M&A activity, and executive changes for accurate lead scoring.
• Built an advanced revenue forecasting system using Python, leveraging the Darts library. Implemented time series models like N-BEATS and others for accurate revenue predictions. Achieved a 25% improvement in prediction accuracy and reduced manual calculation errors by 30%.
• Streamlined the process of generating Monthly Spend reports, Revenue reports, Invoices, and an Attrition Prediction model using Python in Dataiku. Utilized Pandas for data manipulation, Darts for time series forecasting, and Scikit-learn and TensorFlow for machine learning. Automated reporting workflows, reducing manual effort by 40% while improving accuracy and providing actionable insights for better decision-making.