Examensarbeten för masterexamen // Master Theses
Länka till denna samling:
Browse
Browsar Examensarbeten för masterexamen // Master Theses efter Program "Computer science – algorithms, languages and logic (MPALG), MSc"
Visar 1 - 4 av 4
Sökresultat per sida
Sortera efter
- PostA column generation approach to the flexible job-shop problem with ordering requirements on operations(2018) Jonsson, Niclas; Chalmers tekniska högskola / Institutionen för matematiska vetenskaper; Chalmers University of Technology / Department of Mathematical Sciences
- PostConstrained Portfolio Optimization in Liability-Driven Investing(2019) Filip, Hallqvist; Chalmers tekniska högskola / Institutionen för matematiska vetenskaperIn this thesis we formulate and implement a multi-stage portfolio optimization model, and solve it using a genetic algorithm. The goals of the thesis are, apart from formulating and implementing the problem, to estimate suitable parameters for the scenario generation, and to make sure that the problem is solved in a computationally efficient manner. Lastly, we investigate and discuss the performance of the complete system, including financial aspects of the produced solutions, the stability of the solutions, and the computational complexity of the model. We find that our problem formulation is useful, and that it it allows for great flexibility with regards to adding new constraints. We also find that our genetic algorithm solves the problem in reasonable time. Before the model can be used in practice however, results show that it needs to be improved with regards to stability in the solutions.
- PostStocks vs. Bonds A Data-Driven Approach to Asset Allocation Using Machine Learning(2023) Skenderovic, Nermin; Hölvold, Emil; Chalmers tekniska högskola / Institutionen för matematiska vetenskaper; Lemurell, Stefan; Bruinsma, SebastianusThis thesis explores the application of supervised machine learning algorithms to asset allocation strategies with the aim of enhancing investment decision-making processes. Collaborating with Nordea, one of the leading financial institutions in the Nordics, the study was conducted at their Asset & Wealth Management department to investigate the potential of developing a machine learning model, with the goal of improving portfolio performance and reducing risk in the context of a dynamic and uncertain financial market environment. The research begins by analysing the current status of the field, examining the theoretical foundations of asset allocation, and identifying the shortcomings of traditional approaches. Additionally, the thesis raises a nuanced view of quantitative investing, with an in-depth exposition of the most common pitfalls and their consequences. Building on this foundation and previous work, regression and classification algorithms are investigated together with premium financial data as potential solutions to overcome these limitations. Specifically, the Random Forest and XGBoost models are used to forecast movements for the upcoming month in a global stock and bond index. The signals generated by the models are then incorporated into a rule-based allocation model. The findings of this research suggest that machine learning techniques can offer valuable insights and improved performance in asset allocation. The results highlight the potential of these models to identify leading indicators and exploit market inefficiencies, resulting in improved risk-adjusted returns. The best-performing model achieved an alpha of 2.05% during the backtest between 2020 and 2023, accompanied by an increase in Sharpe ratio and a decrease in volatility. However, it is important to note that the effectiveness of machine learning algorithms is heavily dependent on the quality and availability of data, as well as the appropriate selection and calibration of model parameters. Financial markets are dynamic and subject to various factors, so ongoing adjustments are necessary to adapt to changing market conditions and mitigate risks.
- PostThe Oskillator, Artificial Force Field Highway Chauffeur(2020) Larsson, Oskar; Chalmers tekniska högskola / Institutionen för matematiska vetenskaper; Geynts, AlexeyThe fully autonomous vehicle is not here yet, but a first step would be a completely autonomous feature for a simpler subset of scenarios. In this research work, the Oskillator is presented, a combined behavior and trajectory algorithm for a Highway chauffeur based on artificial force fields. At each point in time an acceleration vector is determined by generating an artificial force based on the road and the other vehicles. The force is generated from a set of simpler force components, such as the Lane Component for centering in lane, and the Pass Component for switching lanes behind a slower vehicle, etc. The components are not additive as the logic for traffic behavior is not. Instead, a composition method was developed based on min and max operations. This way the components from different vehicles on the road prevents the influence of the others, a single car is as much an obstruction as three. The force is continuous w.r.t. all inputs and a damping is analytically determined as to avoid oscillations. The host is proven to never engage in a lane switch to a lane of another vehicle with an unsafe longitudinal distance and to stop in time to avoid crashing upon entering the unsafe longitudinal distance behind another vehicle. Experiments have been performed in a simulation environment to assess the behavior of the model. It shows that the host is able to follow the road in lane and pass when appropriate, or approach the desired headway smoothly if unable to pass. The emergent lane switching manoeuvres have a very low lateral velocity, thus the switch takes a long time. Several components could be extracted for standalone use, such as Adaptive Cruise Control or Lane Keep Assistance.