Product Recommendation Analysis Project
Nikita Prasad
Data Scientist
Data Analyst
Data Engineer
Python
SQL
Tableau
Work Process
Data Cleaning: Utilized Excel to clean and preprocess the collected data, ensuring accuracy and consistency.
Data Warehouse Architecture: Designed and implemented a SQL-based Superstore Data Warehouse to store and organize the cleaned data effectively.
Trend Analysis: Conducted a thorough analysis of 10K customer records using SQL queries to identify trends and patterns in sales and customer behavior.
Dashboard Creation: Utilized Tableau to create a Quarterly Sales Forecasting Dashboard, visualizing state-wise distribution of sales and profit time series data. Through which mentioned below insights are extracted insights from the dashboard.
Model Building: Employed Python NLP (Natural Language Processing) models to develop Popularity and Collaborative Recommendation Systems, enabling personalized item suggestions based on user interests.
Tools Used
Excel for Data Cleaning
Tableau for creating dashboard
SQL for analysis
Python for Model Building
Conclusion
In conclusion, the implementation of a SQL-based Superstore Data Warehouse and the analysis of customer records have provided valuable insights for business growth. Through the Quarterly Sales Forecasting Dashboard and the Popularity and Collaborative Recommendation Systems, businesses can make data-driven decisions, enhance customer satisfaction, and drive profitability.
