Know more

Our use of cookies

Cookies are a set of data stored on a user’s device when the user browses a web site. The data is in a file containing an ID number, the name of the server which deposited it and, in some cases, an expiry date. We use cookies to record information about your visit, language of preference, and other parameters on the site in order to optimise your next visit and make the site even more useful to you.

To improve your experience, we use cookies to store certain browsing information and provide secure navigation, and to collect statistics with a view to improve the site’s features. For a complete list of the cookies we use, download “Ghostery”, a free plug-in for browsers which can detect, and, in some cases, block cookies.

Ghostery is available here for free:

You can also visit the CNIL web site for instructions on how to configure your browser to manage cookie storage on your device.

In the case of third-party advertising cookies, you can also visit the following site:, offered by digital advertising professionals within the European Digital Advertising Alliance (EDAA). From the site, you can deny or accept the cookies used by advertising professionals who are members.

It is also possible to block certain third-party cookies directly via publishers:

Cookie type

Means of blocking

Analytical and performance cookies

Google Analytics

Targeted advertising cookies


The following types of cookies may be used on our websites:

Mandatory cookies

Functional cookies

Social media and advertising cookies

These cookies are needed to ensure the proper functioning of the site and cannot be disabled. They help ensure a secure connection and the basic availability of our website.

These cookies allow us to analyse site use in order to measure and optimise performance. They allow us to store your sign-in information and display the different components of our website in a more coherent way.

These cookies are used by advertising agencies such as Google and by social media sites such as LinkedIn and Facebook. Among other things, they allow pages to be shared on social media, the posting of comments, and the publication (on our site or elsewhere) of ads that reflect your centres of interest.

Our EZPublish content management system (CMS) uses CAS and PHP session cookies and the New Relic cookie for monitoring purposes (IP, response times).

These cookies are deleted at the end of the browsing session (when you log off or close your browser window)

Our EZPublish content management system (CMS) uses the XiTi cookie to measure traffic. Our service provider is AT Internet. This company stores data (IPs, date and time of access, length of the visit and pages viewed) for six months.

Our EZPublish content management system (CMS) does not use this type of cookie.

For more information about the cookies we use, contact INRA’s Data Protection Officer by email at or by post at:

24, chemin de Borde Rouge –Auzeville – CS52627
31326 Castanet Tolosan CEDEX - France

Dernière mise à jour : Mai 2018

Menu Logo Principal Logo AgroParisTech_University

Economie Publique

UMR Economie Publique

Thesis Defence

Rotem Zelingher will defend her thesis on Monday, November 29th 2021.

At AgroParisTech, 16 rue Claude Bernard à Paris, at 13h 30, amphi Coleou, Rotem Zelingher will defend her thesis : "Agricultural Commodity Price Forecasting Using Comprehensive Machine-Learning Techniques".



Would it be possible to develop a forecasting tool for agricultural commodity prices that is both accurate and interpretable, and above all, accessible to the general public? Thanks to such a tool, the forecasting and analysis of food prices could cease being a domain exclusively reserved to scientists, economists and financiers, and turn into an implementable instrument used by whoever is concerned by food security. Such a tool would allow those who do not have the financial capacity or the appropriate technical background to forecast agricultural commodity prices at least a month in advance. Ideally, this tool can be updated
sequentially, so that its results could evolve with the market.

This PhD explores the feasibility of this idea in three parts.

The objective of the first part is to test the ability of several statistical and machine learning models to simulate changes in maize prices based on annual changes in maize production and yield observed in major producing regions. Two approaches are examined: quantitative, allowing to simulate price variations continuously, and binary classification, to enable calculating the probability of price increases or decreases. In this first part, the models are fitted into the data, evaluated using statistical criteria, and finally, identify regions that strongly influence price variations. The results show that, relative to the last quarter of the year, maize production in North America has, by far, the highest impact on global crop prices. They also demonstrate the possibility to establish a relationship between production variations in North America and variations in the world price of maize.

The second part of the thesis applies the models developed in the first part and adapt them to produce monthly forecasts of maize prices. We compare the performance of these models to that of forecasting techniques often used for time series analysis. We show that, for short-term forecasts usually up to three months, time series analysis techniques have several advantages. First, they are generally more accurate; second, they allow the performance of direct price change forecasting without using any additional information. On the other hand, to forecast prices at longer time horizons, we would usually prefer machine learning models, as they yield results of lower error. These algorithms have an additional advantage: they can diagnose probable causes of extreme price variations and identify which production shocks cause these variations.

Finally, in the third part, we extend the one-crop model to consider two other very different crops - soybeans (a legume that constitutes the world-main source of vegetative protein) and cocoa (a crop produced in only a few countries located in the tropics). We evaluate the forecasting ability of the techniques developed in the previous stages to predict price changes for soybeans and cocoa. Additionally, we test the sensitivity of the results relative to three geographic scales: regional, national and continental. Also demonstrated in this chapter is the application of machine learning methods to identify which production shocks drive price shocks. Overall, this thesis shows that machine learning methods are a potential tool for understanding and forecasting the impact of agricultural production on price variations. These approaches can be easily implemented since they rely on publicly available data, accessible via public website. These tools can thus contribute to democratising the analysis and forecasting of variation in agricultural commodity prices.