Register now After registration you will be able to apply for this opportunity online.
This opportunity is not published. No applications will be accepted.
Predicting alfalfa hay prices using machine learning
The aim of this master thesis is to improve forecast of alfalfa hay prices in the US using machine learning, accounting for records of future prices and other macro indicators as well as ex-ante and ex-post weather variables.
**Background:**
Hay is an important source for forage and trade of hay is an important component for farmers. However, markets for hay are often less transparent and less developed than for other crops. Thus, the knowledge about prices and price predictions is often scare if compared to other crops.
This thesis will focus on the US market and alfalfa hay, which is the third most harvested crop (USDA-NASS 2019). Within hay, alfalfa hay plays an important role in the US. Alfalfa hay is regularly sold at auctions and current prices are available online for some locations, which makes the price more transparent than for other hay. However, alfalfa hay is less transparent than some of its other substitutes, e.g. soybean, which are treaded at large scales and future contracts to hedge risks are available. At the end of the last century, forecasting (alfalfa) hay prices received more attention in the scientific community (Blake and Clevenger 1984, Blake and Catlett 1984, Myer and Yanagida 1984, Konyar and Knapp 1988, Skaggs and Snyder 1992, Brorsen 1994), while in the recent past only two studies exist focused on it (Bazen et al. 2008, Diersen 2008).
**Goal:**
The specific aim of this master thesis is to forecast alfalfa hay prices in the US using machine learning. In more detail it should be tested: i) if we can predict alfalfa hay prices using agriculture future prices and other macro indicators, ii) if we can improve the prediction by including weather variables in the analysis.
**References:**
Blake, M. J. and Clevenger, T. (1984). A Linked Annual And Monthly Model For Forecasting Alfalfa Hay Prices. Western Journal of Agricultural Economics, 9:1-5.
Blake, M. L. and Catlett, L. B. (1984). Cross Hedging Hay Using Corn Futures: An Empirical Test. Western Journal of Agricultural Economics, 9:1-8.
Brorsen, W. (1994). Forecasting Monthly Alfalfa Hay Prices: An Appraisal of Econometric and Time Series Models. SAEA annual meeting.
Konyar, K. and Knapp, K. (1988). Market analysis of alfalfa hay: California case. Agribusiness, 4:271-284.
Myer, G. L. and Yanagida, J. F. (1984). Combining Annual Econometric Forecasts With Quarterly Arima Froecasts: A Heuristic Approach. Western Journal of Agricultural Economics, 9:1-7.
Skaggs, R. K. and Snyder, D. L. (1992). A comparison of selected methods for forecasting monthly alfalfa hay prices. Agribusiness, 8:309-321.
USDA-NASS (2019). Crop Production Annual Summary. Technical report, United States Department of Agriculture
**Background:**
Hay is an important source for forage and trade of hay is an important component for farmers. However, markets for hay are often less transparent and less developed than for other crops. Thus, the knowledge about prices and price predictions is often scare if compared to other crops. This thesis will focus on the US market and alfalfa hay, which is the third most harvested crop (USDA-NASS 2019). Within hay, alfalfa hay plays an important role in the US. Alfalfa hay is regularly sold at auctions and current prices are available online for some locations, which makes the price more transparent than for other hay. However, alfalfa hay is less transparent than some of its other substitutes, e.g. soybean, which are treaded at large scales and future contracts to hedge risks are available. At the end of the last century, forecasting (alfalfa) hay prices received more attention in the scientific community (Blake and Clevenger 1984, Blake and Catlett 1984, Myer and Yanagida 1984, Konyar and Knapp 1988, Skaggs and Snyder 1992, Brorsen 1994), while in the recent past only two studies exist focused on it (Bazen et al. 2008, Diersen 2008).
**Goal:**
The specific aim of this master thesis is to forecast alfalfa hay prices in the US using machine learning. In more detail it should be tested: i) if we can predict alfalfa hay prices using agriculture future prices and other macro indicators, ii) if we can improve the prediction by including weather variables in the analysis.
**References:**
Blake, M. J. and Clevenger, T. (1984). A Linked Annual And Monthly Model For Forecasting Alfalfa Hay Prices. Western Journal of Agricultural Economics, 9:1-5.
Blake, M. L. and Catlett, L. B. (1984). Cross Hedging Hay Using Corn Futures: An Empirical Test. Western Journal of Agricultural Economics, 9:1-8.
Brorsen, W. (1994). Forecasting Monthly Alfalfa Hay Prices: An Appraisal of Econometric and Time Series Models. SAEA annual meeting.
Konyar, K. and Knapp, K. (1988). Market analysis of alfalfa hay: California case. Agribusiness, 4:271-284.
Myer, G. L. and Yanagida, J. F. (1984). Combining Annual Econometric Forecasts With Quarterly Arima Froecasts: A Heuristic Approach. Western Journal of Agricultural Economics, 9:1-7.
Skaggs, R. K. and Snyder, D. L. (1992). A comparison of selected methods for forecasting monthly alfalfa hay prices. Agribusiness, 8:309-321.
USDA-NASS (2019). Crop Production Annual Summary. Technical report, United States Department of Agriculture
Not specified
Supervisors: Sergei Schaub and Prof. Robert Finger. Pleas contact Sergei Schaub: seschaub@ethz.ch
Supervisors: Sergei Schaub and Prof. Robert Finger. Pleas contact Sergei Schaub: seschaub@ethz.ch