Problem Description: Sustainability of the human race in different parts of the world is
challenged by the shortage of food. The world population has grown six hundred
percentage - from one billion to about six billion - in the last two hundred years. According
to the Population Institute, roughly, 230 thousand more babies are born every day. The
World Food Programme estimates that about 795 million people do not have adequate
food to lead a healthy life. About 3.1 million children die every year because of poor
nutrition. On the other hand, land used for farming has been decreasing which makes the
burden of food shortage acute. Regardless, simply attempting to increase the land
available for farming is unlikely to sustain the needed food supply. To address this great
problem, this project expects you to develop an analytics framework to aid soybean
farmers select up to a given number of varieties of soybeans from a large set of available
varieties to maximize the yield at a target farm.
Every year soybean farmers make decisions about the varieties to be grown at their farm.
While making this decision, they consider uncertainty due to weather, soil conditions, and
yield studies of different varieties. They could choose just one variety or a mix of few
varieties to hedge against uncertainties. You are expected to utilize the dataset provided
to propose a framework which integrates descriptive, predictive, and prescriptive analytics
to optimally select up to five varieties of soybeans.
Deliverables:
1. Perform exploratory data analytics to unearth patterns in the given data and utilize
those patterns in making predictions and prescriptions.
2. Construct one or more prediction models to predict yield of different experimental
varieties.
3. Optimize the portfolio of (experimental) varieties to be grown at the target farm.
The optimal portfolio can have at most 5 varieties of soybean. It is not necessary
but you are welcome to use the methods you learn in prescriptive analytics class
to construct the optimal portfolio.