eprintid: 195
rev_number: 4
eprint_status: archive
userid: 6
dir: disk0/00/00/01/95
datestamp: 2008-11-03
lastmod: 2015-05-29 19:49:09
status_changed: 2009-04-08 16:55:44
type: report
metadata_visibility: show
item_issues_count: 0
creators_name: Ware, Tony
contributors_name: Bos, Len
contributors_name: Bondy, Brad
contributors_name: Amiraslani, Amir
contributors_name: Holloway, Thomas
contributors_name: Li, Hua
contributors_name: Mizani, Maryam
contributors_name: Mohajer, Mahyar
contributors_name: Nouri, Comron
contributors_name: Orosi, Gergeli
contributors_name: Rezvani, Nargol
contributors_name: Xu, Liang
contributors_name: Xu, Oulu
title: Adaptive Statistical Evaluation Tools for Equity Ranking Models
ispublished: pub
subjects: finance
studygroups: ipsw9
companyname: Genus Capital Management
full_text_status: public
abstract: A major challenge in the investment management business is to identify which stocks are likely to outperform in the future, and which are likely to perform relatively poorly. To this end the strategy adopted by Genus is to identify factors (auxiliary information about the stock such as earnings-to-price ratio or dividend yield) that they believe are associated with future out-performance (i.e. factors that have predictive ability). The best of these factors are then combined (Genus use a weighted average) into a model which is used to rank the universe of stocks month-by-month. This ranking is then used to as the input to a trading strategy, resulting in a modified portfolio.

Genus had provided us with sample data, consisting of just over 12 years worth of monthly returns on a universe of 60 stocks, along with time series of 34 factors for each of the stocks. Using these data, the approach was to build software (MATLAB) models for:

1. ranking the stocks based on factor information;

2. implementing a trading strategy based on a stock ranking and assessing the performance of a given trading strategy by looking at measures such as hit ratio, information ratio and spread.

The IPSW team implemented a simplified trading strategy of selling the entire portfolio each month, and using the proceeds to invest equally in the top 20% of stocks as given by the computed ranking. They also implemented the following measures of portfolio performance: excess return, hit ratio and information ratio.
problem_statement: Genus Capital Management offer investment portfolios for private individuals and families, trusts, foundations and pension funds with a variety of flavours. Each portfolio consists of investments in stocks from some given ‘universe’. Competitive advantage comes from consistently out-performing competing funds. One of the approaches that Genus use to achieve competitive advantage is to make use of auxiliary information about the stocks in the universe in deciding how to adjust their portfolio month by month.

The challenge posed for the study group is:

1. to recommend adaptive statistical evaluation tools (alternatives to out-of-sample tests) that could be used to improve confidence in a model and to help decide in a timely fashion if a new factor should be added to a model, or if an existing factor should be removed;

2. to suggest algorithms that could be used to dynamically update the models with a view to exploring a dynamic strategy in which model factors and weights are updated monthly based on the evaluation measures.
date: 2005
date_type: published
pages: 13
citation:   Ware, Tony  (2005) Adaptive Statistical Evaluation Tools for Equity Ranking Models.  [Study Group Report]     
document_url: http://miis.maths.ox.ac.uk/miis/195/1/genus.pdf