Browsing by Author "Bergander, William"

Now showing 1 - 2 of 2

Deep Learning Cocoa Price Prediction with Weather Data
(2025-07-06) Bergander, William; University of Gothenburg/Graduate School; Göteborgs universitet/Graduate School
Climate-induced volatility in global cocoa markets poses significant challenges to producers and stakeholders, notably evidenced by the severe price surge in late 2024 following adverse weather events. This thesis investigates whether integrating weather variables, specifically temperature and precipitation, with historical cocoa futures prices can enhance predictive accuracy using Long Short-Term Memory (LSTM) neural networks. Leveraging daily price data from the ICE Futures U.S. exchange (1980–2025) and comprehensive meteorological data from the ERA5 dataset across key cocoa-producing regions, multiple LSTM models, including global and localised scales, were developed and evaluated. This deep learning approach to cocoa price prediction, incorporating meteorological inputs, addresses a gap in existing forecasting literature. Contrary to prior studies and expectations, models incorporating detailed weather indicators did not improve forecasting accuracy over a baseline model relying solely on historical prices, which achieved a notably high predictive performance (R² ≈ 0.998). A global-scale model using average climate indicators matched the baseline model's predictive power (R² ≈ 0.986), while more localised models underperformed significantly. Robustness tests, including permutation importance analyses, confirmed that historical price data predominantly drove the levels of predictive power, respectively, with weather variables providing minimal incremental value. This lack of improvement suggests that weather impacts may already be priced into market trends due to market efficiency or were too complex to capture with the utilised naive LSTM model. These results highlight methodological limitations, particularly the absence of cocoa yield data, which likely restricted the ability to capture the indirect economic impacts of weather conditions accurately. Future research incorporating this cocoa yield data within a structured causal framework, such as the DeepIV method, has the potential to more precisely model the economic transmission from climate impacts to the global cocoa market pricing.
Nedstängda samhällen - försämrad skolgång?
(2022-09-05) Bergander, William; Brattlund, Viking; University of Gothenburg/Department of Economics; Göteborgs universitet/Institutionen för nationalekonomi med statistik
This paper is researching the economic impact of Covid-19 restrictions on the performance of students in primary school in what are broadly categorized as low- and middle-income countries by the World Bank. This is done in the context of many studies being done on the academic impact of the pandemic and the accompanying restrictions, but only on specific smaller regions and nations or with the focus on more developed nations. This broad study on a large portion of what’s categorized as low- and middle-income countries is done with 4 iterations of an OLS regression. This is then controlled with a Mann-Whitney U test to determine if there is any discernible correlation between a high level of lockdown stringency and a low level of primary school completion rate. Though the results of this paper are statistically insignificant, most likely due to the low amount of data points, they are also potentially economically insignificant. The resulting correlation given is so small that it might as well be disregarded as economically insignificant if it were statistically significant. The paper concludes that there is a great need for a bigger data coverage on this very important topic, to discern the long-term ramifications of this potential impact on education. We should also gather more data for insight into how to proceed with likewise policy in the future since the risk of a new and even worse pandemic is always potentially on the event horizon.