Year: 2016, 2016
Member of: Trent University Graduate Thesis Collection
Abstract: <p>This thesis is intended to support dependent-on-crops farmers to hedge the price risks of their crops. Firstly, we applied one-factor model, which incorporated a deterministic function and a stochastic process, to predict the future prices of crops (soybean). A discrete form was employed for one-month-ahead prediction. For general prediction, de-trending and de-cyclicality were used to… more Year: 2016, 2016
Member of: Trent University Graduate Thesis Collection
Abstract: <p>We propose a stochastic weather model based on temperature, precipitation, humidity and wind speed for Qatar, as a representative arid region, in order to obtain simulated values for a drought index. As a drought index, the Reconnaissance Drought Index (RDI) is commonly accepted in agriculture and is used to measure drought severity. It can be used to price weather derivatives to help… more Year: 2016, 2016
Member of: Trent University Graduate Thesis Collection
Abstract: <p>In the context of Real-Time Bidding (RTB) the machine learning problems of</p><p>imbalanced classes and model selection are investigated. Synthetic Minority Oversampling Technique (SMOTE) is commonly used to combat imbalanced classes but a shortcoming is identified. Use of a distance threshold is identified as a solution and testing in a live RTB environment shows significant… more
