Seed Stocking Via Multi-Task Learning

TL;DR

This paper presents a multi-task learning framework to predict seed demand by estimating yield and risk for various seed varieties across locations, aiding seed stock planning under weather uncertainty.

Contribution

It introduces a novel analytical framework using multi-task learning to improve seed demand estimation by leveraging data across varieties and balancing yield with risk.

Findings

Multi-task learning effectively predicts seed yield and risk.

The framework improves seed demand estimation accuracy.

Top seed varieties can be selected to optimize yield and risk tradeoffs.

Abstract

Sellers of crop seeds need to plan for the variety and quantity of seeds to stock at least a year in advance. There are a large number of seed varieties of one crop, and each can perform best under different growing conditions. Given the unpredictability of weather, farmers need to make decisions that balance high yield and low risk. A seed vendor needs to be able to anticipate the needs of farmers and have them ready. In this study, we propose an analytical framework for estimating seed demand with three major steps. First, we will estimate the yield and risk of each variety as if they were planted at each location. Since past experiments performed with different seed varieties are highly unbalanced across varieties, and the combination of growing conditions is sparse, we employ multi-task learning to borrow information from similar varieties. Second, we will determine the best mix of seeds for each location by seeking a tradeoff between yield and risk. Third, we will aggregate such mix and pick the top five varieties to re-balance the yield and risk for each growing location. We find that multi-task learning provides a viable solution for yield prediction, and our overall analytical framework has resulted in a good performance.