University of Twente Student Theses

Login

Algorithmic investing within the philosophy of the Basis Zero experiment.

Wit, M.L. de (2017) Algorithmic investing within the philosophy of the Basis Zero experiment.

This is the latest version of this item.

[img]
Preview
PDF
5MB
[img] PDF
Restricted to Restricted

5MB
Abstract:We created an algorithm that automatically invests pension capital with costs that stay under 10 basis points per year. When the participant retires, the total capital position is transferred to an annuity from which our performance can be measured by the replacement rate: the ratio between earnings before and after retirement. A limited investment universe is used including 10 indices on the following asset classes: equities , real estate, commodities, credits/treasuries and cash. The solution is based on a mean variance strategy that is tested on historical and simulated data. Our datasets are simulated by a geometric Brownian motion, general historical simulation and extensions based on an exponential weighted moving average where recent or low interest rate scenarios get more weight. Compared to our benchmark APG our results score well on mean and median values but fail on the dispersion of the results where low Values at Risk are the result. As the risk on insufficient results is substantial APG’s own performance is still preferred due to the decent, stable results.
Item Type:Essay (Master)
Faculty:BMS: Behavioural, Management and Social Sciences
Subject:31 mathematics, 83 economics
Programme:Industrial Engineering and Management MSc (60029)
Link to this item:http://purl.utwente.nl/essays/71912
Export this item as:BibTeX
EndNote
HTML Citation
Reference Manager

 

Repository Staff Only: item control page