By Hristina Kostadinova, Business Analyst Intern @ Enhanced Retail Solutions LLC

One of the most rewarding parts of my internship was having the opportunity to build an Open-to-Buy (OTB) forecast from the ground up. Coming into this project, I had experience working with data and retail analytics, but I had never built a tool that directly supported business planning decisions. This project showed me how data can be used to solve real business problems and help companies plan ahead.

Bringing the Data Together

What initially seemed like a straightforward forecasting project quickly became much more complex. The data needed for the model was spread across multiple sources, each containing a different piece of the inventory planning process. The retailer’s inventory, wholesale inventory, production schedules, sales forecasts, and product attributes all existed in separate datasets. Before any forecasting could happen, these pieces had to be connected and transformed into a structure that could support the model.

Much of my time was spent understanding how these different data sources related to one another. Every table answered a different question. Some showed what inventory was currently available, others showed what inventory was expected to arrive in the future, and others projected sales over the next several months. Building the forecasting engine required combining all these perspectives into a single model.

Data Validation

One thing I learned during this project was how important data validation is. Building the calculations was only part of the process. It was just as important to make sure the results actually made sense. Small changes in the logic could have a large impact on future inventory projections, so a significant amount of time was spent testing calculations, investigating unexpected results, and refining the model.

After completing the SQL engine, I connected the results to Power BI and developed an interactive dashboard that allows users to explore inventory projections and purchasing recommendations. Seeing the finished dashboard was rewarding because it brought all of the data together into a tool that users could easily explore and understand.

Open to buy projection using starting inventory, on order, forecast sales and a Budget.

Final Thoughts 

This project reinforced something I have learned throughout my internship: analytics is not just about writing code or building reports. It is about understanding a problem and developing a solution that helps people make better decisions. Building OTB challenged me technically and gave me a better understanding of how data supports inventory planning and forecasting.