In this project machine learning techniques were used to generate technical trading strategies in the US interest rate swap markets. Leela, a correlation algorithm that is closely related to autoregression, was developed to detect short term repeating patterns to predict future market moves. This algorithm exhibited a Sharpe Ratio of 1 when applied to a single swap. When additional swaps were u...

Eling and Schuhmacher (2007) compared the Sharpe ratio with other performance measures and found virtually identical rank ordering using hedge fund data. They conclude that the choice of performance measure has no critical influence on fund evaluation and that the Sharpe ratio is generally adequate for analyzing hedge funds. Nevertheless, their analysis does not include the class of tailor-made...

This paper proposes a method which combines a clustering technique with asset allocation methods, to improve portfolio Sharpe ratios and weights stability. The portfolio weights are computed based on cluster members and cluster portfolios, which are decided by an optimal cluster pattern. The optimized cluster pattern tells the belonging of assets to particular clusters, which is identified by u...

The problem of capital allocation to a set of strategies could be partially avoided or at least greatly simplified with an appropriate strategy approval decision process. This paper proposes such procedure. We begin by splitting the capital allocation problem into two sequential stages: Strategy approval and portfolio optimization. Then we argue that the goal of the second stage is to beat a na...

Herein is an incomplete collection of facts about the Sharpe ratio, and the Sharpe ratio of the Markowitz portfolio. Connections between the Sharpe ratio and the t-test, and between the Markowitz portfolio and the Hotelling T 2 statistic are explored. Many classical results for testing means can be easily translated into tests on assets and portfolios. A ‘unified’ framework is described which c...

We propose a new luminosity function, V ð1Þ, that improves upon the original CIE 1924 Vð1Þ function and its modification by D. B. Judd (1951) and J. J. Vos (1978), while being consistent with a linear combination of the A. Stockman & L. T. Sharpe (2000) long-wavelength-sensitive (L) and middle-wavelength-sensitive (M) cone fundamentals. It is based on experimentally determined 25 Hz, 2diameter,...