Application of Data Science Techniques to Market Gardening (A Case Study)

Purpose 

The goals of this study were achieved using data analysis techniques to provide business intelligence to market farmers.  This business intelligence included: 

• Recommended plantings.   
• Weekly Total Sales Forecast. 
• Weekly Demand Forecast. 
• Annual Sales Forecast.  

Objectives 

The models utilized collected and researched data to generate weekly harvest dates, plant yields, market yields, market demands, and sales information. The models used this information to: 

• Develop a model for planting that optimizes sales and profit.  
• Predict the weekly vegetable yields for purchase at the market.  
• Forecast farm growth for future profit goals. 
• Develop models that accounted for seasonal variation of plants, garden planting area, and varying customer demand. 

Conclusions 

Data analytics is typically discussed in terms of big data, large databases, executive business intelligence, and associated with large corporations.  However, business is business regardless of size.  The project showed data analytics can model market garden productivity with plant yield analysis.  Market yield analysis represented quality control and production issues.  Sales analysis modeling revealed future profits.   Business optimization recommended plant type and quantity for maximum profit.  The study was a cursory application of several data analysis techniques, but it demonstrated the application of these techniques for any small business.