Inspiration
The inspiration behind our project stemmed from recognizing the critical role that strategic facility locations play across industries, significantly impacting operational efficiency and market accessibility. Traditional site selection methods often rely on intuition and outdated practices, prompting our team to pursue a more modern, data-driven approach to optimize tissue mill locations.
What it does
Our solution strategically identifies optimal locations for tissue mills by integrating data on regional demand distribution, resource availability, and accessibility to major markets. It prioritizes placement within a 500-mile radius of major U.S. metropolitan areas to minimize transportation costs and improve delivery efficiency. Our model specifically targets regions with the highest tissue consumption such as the Southeast, Farwest, and Mideast.
How we built it
We built our solution by harnessing diverse datasets including Census ACS data (DP02, DP03, DP05), Forisk's 2023 Timber Availability report, and the US Bureau of Economic Analysis' tissue consumption data. Our methodology involved integrating these datasets based on geographic identifiers and coordinates, cleaning and normalizing data to ensure consistency and quality, and calculating composite scores for each location based on weighted factors including timber availability, population density, and regional demand. We used Python and Tableau to analyse and solve the problem
Challenges we ran into
We faced challenges primarily related to data integration, particularly in harmonizing disparate datasets with varying formats and metrics. Ensuring accuracy during the normalization of data, addressing missing values, and assigning appropriate weights to different factors required considerable iterative adjustments to refine the composite scoring model.
Accomplishments that we're proud of
We are proud to have developed a robust, data-driven model that successfully identifies and prioritizes optimal mill locations. Specifically, we identified Atlanta, GA; Portland-Vancouver; and Jackson, MS as top locations, each offering unique logistical advantages. Our model significantly improves decision-making speed, reduces bias, and provides actionable insights backed by concrete data.
What we learned
Throughout this project, we learned the importance of meticulous data preprocessing and the impact of comprehensive data integration on strategic decision-making. Additionally, we gained deeper insights into logistical optimization, regional market analysis, and the utility of composite scoring methodologies for complex business decisions.
What's next for Kimberly Clark
The next steps involve implementing this model in real-world scenarios, continuously refining it with updated and expanded datasets, and potentially incorporating additional predictive analytics capabilities. We aim to extend this analytical framework to other strategic decision-making processes within Kimberly Clark, enhancing overall operational efficiency and maintaining competitive advantage.
Log in or sign up for Devpost to join the conversation.