PRODUCT/MARKETING PROJECTS
Marketing Mix Modeling
Utilized Python for detailed marketing mix modeling, incorporating advanced attribution models and thorough channel analysis. Leveraged statistical methods and machine learning algorithms for granular insights into the customer journey. Applied ad budget optimization to strategically allocate resources across channels, ensuring adjustments for optimal performance and enhanced ROI. The data-driven strategy improves resource allocation, directing efforts to the most lucrative channels and contributing to overall marketing success.
Customer Segmentation for Targeted Ads
Leveraged the power of K-Means clustering from the SciKit Learn library to effectively categorize and segment the bank's diverse customer base, enabling the strategic deployment of highly tailored advertising campaigns. Employed Principal Component Analysis (PCA) to streamline the data by reducing dimensionality, ensuring a more efficient and insightful classification process. This initiative will not only improve campaign precision but also contribute to enhancing overall customer engagement and satisfaction.
Github link coming soon
Website User Behavior Analysis
Conducted Website User Behavior Analysis through the integration of Google Analytics, utilizing SQL queries for robust data extraction and analysis. Employed advanced statistical techniques, including A/B testing, to iteratively refine website design parameters. This data-driven approach will result in a significant enhancement of user engagement metrics and a notable increase in conversion rates, showcasing proficiency in analytics, SQL, and strategic optimization methodologies.
Customer Churn Prediction
Developed a Customer Churn Prediction model using R including comprehensive data preprocessing, advanced feature engineering, and machine learning model development, achieving an accuracy of 90.7%. Implemented cutting-edge methodologies, such as ensemble techniques and hyperparameter tuning, to optimize model performance. Utilized Power BI for the creation of interactive and visually insightful reports, instrumental in guiding targeted retention efforts and strategically reducing churn rates.
.png)
AdPulse: Generate short Ads for your Product
Leveraged the capabilities of the open-source Large Language Model, Bloom 1b7, through a meticulous fine-tuning process using the Parameter Efficient Fine Tuning (PEFT) methodology. Conducted comprehensive training on a diverse dataset, encompassing product descriptions and ads, resulting in the model's proficiency in generating compelling short advertisements based on input product names and descriptions. The fine-tuned model was seamlessly deployed on the Hugging Face platform