Pravalika Parankusham

Detail-focused Data Analyst with proven ability to understand customer requirements and translate into actionable project plans. Dedicated and hard-working with passion for Big Data.

1. Inventory Optimization and Demand forecasting:

• Analyzed historical sales data, inventory levels of various product categories to forecast demand of those products.
• Implemented time series forecasting analysis to predict the future demand of the products and developed models to optimize inventory levels based on various constraints.
• Attained a 10% reduction in inventory holding costs and also reduction in stockouts

2. Social Media Sentiment Analysis

• Conducted sentiment analysis of social media mentions to analyze public sentiment towards brand. Collected data from various social media platforms using web scraping technique.
• Applied NLP techniques to classify data and extract sentiment scores. Presented the insights and trends of sentiment analysis using dashboards.
• Improved active response to negative sentiments by engaging with customers and improved brand perception.

3. Pricing Strategy Optimization:

• Conducted market analysis which includes understanding different customer segments, pricing offered by other competitors, trends in industry for key products.
• Developed dynamic models to cater to different factors and performed A/B tests to evaluate impact of pricing changes on sales volume, revenue and profit.
• Implemented dynamic pricing algorithms resulting in 5% increase in average order value and improved customer satisfaction.

4. Customer Churn prediction and Retention strategy:

• Developed a predictive model to identify customers at risk of churn and implemented targeted retention strategies to reduce customer churn rates.
• Developed churn prediction model to predict the probability of customer churn depending on the past data available. Performed customer segmentation based on the churn scores and identified the customers who need to be targeted the most for retention.
• Implemented personalized retention strategies to see whether there is a decrease in customer churn. Achieved a 12% reduction in the churn rate and improved customer loyalty.

5. Customer Segmentation Analysis:

• Utilized data based techniques to implement customer segmentation using RFM and clustering techniques to identify customers who add more value.
• Derived new features and metrics to identify customer behavior. Used clustering techniques such as K-means to group customers into segments based on their similarity in characteristics and behavior.
• Designed personalized marketing campaigns for each customer segment based on their behavior, which increased customer engagement by 15% and sales by 10%.