Continuous affective self-reports are intrusive and expensive to acquire, forcing researchers to use alternative labels for the construction of their predictive models. The most predominantly used labels in literature are continuous perceived affective labels obtained using external annotators. However an increasing body of research indicates that the relation between expressed emotion and experienced emotion might not be as apparent as previously assumed. Retrospective self-reports provided by participants do capture experienced emotion, but models applied on these labels suffer from the lack of continuous annotations during training. In this work, we aim to answer whether this lack of temporal information can be remedied by using continuous external annotations as proxies for experienced emotion over time. Furthermore, we investigate whether weakly-supervised models can generate accurate continuous annotations to reduce the annotation burden for large datasets. Our results indicate that external annotation sequences bear little significant information for the prediction of self-reports. However, forcing models to reflect changes in external annotations by training models in a multitask fashion improves model performance, suggesting that such temporal supervision helps models to distinguish relevant segments in input data. Besides this, we find that weakly-supervised models can to a certain extent capture changes over time, but in general yield poor results compared to fully-supervised models.

As Machine Learning is becoming more accessible to small businesses, thanks to the rapid advance in computing power, smaller start-ups such as Sjauf (a ride sharing start-up) are starting to get interested in implementing Machine Learning solutions in their product. Sjauf needed a system that could automatically tell its customers how much a certain trip would cost them. Using this information multiple different models were developed and integrated into an ensemble. This ensemble as well as the models used by it were then used for price prediction. This project is a proof of concept to show that Machine Learning is capable of solving this problem in real time.

After researching state of the art Machine Learning models for price recommendation, the architecture of the system was designed. The supplied data was preprocessed, after which a custom Genetic Algorithm was developed for optimising models and ensembles. After validation on real-life company data, a comparison using empirical metrics was conducted. We use these empirical metrics to show that a bagging ensemble is the most efficient and accurate model for this purpose. This bagging ensemble outperformed the currently implemented functions, whilst adhering to the set boundaries on response times. Lastly, recommendations are made to the company with an overview of potential future work in this subject.