Daman Deep

Price Prediction Model(Re-Commerce)

• Developed predictive model Random Forest to forecast device volume, and determine optimal offer prices for used mobile phones dropped in kiosks using Python(Jupyter Notebook) with AWS SageMaker.
• Utilized Snowflake, SQL queries, to efficiently analyze vast datasets and determine optimal pricing strategies for over 2.3 million devices processed through kiosks
• Collaborated with business stakeholders across multiple functions to understand their analytical needs and develop solutions accordingly.

Agent Persona

• Developed LightGBM model using Python to identify the attributes of ideal financial professional(target persona) or Selling Agent for major US Firm.
• Utilized AWS Redshift to analyze a dataset comprising 108,000 USA-based Insurance Agents, encompassing firm demographics and other relevant factors.
• Utilized k-means clustering to analyze traits of selling agents and categorize them based on product sales.Leveraged this data to forecast the specific products Non Selling agents would likely sell, optimizing targeting strategies

Outdoor Media Planning

• Utilized k-means clustering to analyze demographic data and identify target locations for advertisement placement in different cities of India using Python, Google Maps APIs.
• Leveraged insights on population demographics, such as age groups and gender distribution, to strategically place advertisements based on client preferences, such as promoting medicines near hospitals."