Jake Ansell

Measuring retail company performance using credit scoring techniques

Abstract This paper discusses models for evaluating credit risk in relation to the retailing industry. Hunt’s [Hunt, S.D., 2000. A General Theory of Competition. Sage Publications Inc., California] Resource–Advantage Theory of Competition is used as a basis for variable selection, given the theory’s relevancy to retail competition. The study focuses on the US retail market. Four standard credit scoring methodologies: Naive Bayes, Logistic Regression, Recursive Partitioning and Artificial Neural Network, are compared with Sequential Minimal Optimization (SMO), using a sample of 195 healthy companies and 51 distressed firms over five time periods from 1994 to 2002. The five methodologies performed well in predicting default particularly one year before financial distress. Prediction remained sound even five years before distress with accuracy rates above 78% and AUROC values above 0.79. No single methodology, however, had the best classification ability across different time scales and variable sets. External environmental influences exist, but these influences are weak. In terms of similarity with Moody’s ranking, both SMO and logistic regression models are better than the neural network model, with SMO being slightly better than logistic regression.

Predicting default of a small business using different definitions of financial distress

The paper introduces a number of risk-rating models for UK small businesses applying an accounting-based approach, which uses financial ratios to predict corporate bankruptcy. An enhancement to these models is considered through features typical to retail credit risk modelling. A common problem of default prediction consists in the relatively small number of bankruptcies or real defaults available for model-building. In order to expand the ‘default’ group beyond bankrupt companies, the paper considers adopting four different definitions of ‘a failing business’ by investigating combinations of financial distress levels. The impact of each default definition on the choice of predictor variables and on the models predictive accuracy is explored. In addition, the paper examines the value of categorizing financial ratios used as predictor variables.

Modelling profitability using survival combination scores

Abstract The paper presents the first empirical investigation of the relationship between present value of net revenue from a revolving credit account and times to default and to second purchase. The analysis is based on the data for a store card which is used to buy ‘white’ durable goods in Germany. It is demonstrated that there exists a relationship between the above given measures. It appears that there is a scope for improving profit if an application for a store card is assessed by using a model which estimates the revenue and includes the survival probability of default and the survival probability of second purchase (a survival combination model) rather than merely a static probability of default predicted by a logistic regression.

Analysing maintenance data to gain insight into systems performance

The high cost of maintenance in the processing industry implies the need for optimal planning of maintenance strategy. In order to achieve this there is a need to understand the underlying failure processes, which are often very complex. In this paper, a new semi-parametric approach, combining Cox regression with density kernal smoothing, is introduced to estimate the underlying performance. The approach has been applied to several processes and it allowed insight into each process, which would not have been achieved if traditional approaches had been used. Particularly, the refurbishment of processes had a significant impact on the rate failure. This paper concludes by assessing this impact of refurbishment on the maintenance programme.

Modelling take-up and profitability

We use response data collected by a lender to estimate the probabilities of loan offers being accepted by the applicants and the survival probabilities of default and of paying back early. Combining all those together we estimated the expected profit surface for the lender at the time of application before making an offer to an applicant. The results show how a lender could find the optimal interest rate to increase the expected profit or its market share. We also consider how different optimal decision policies could be applied to different market segments.

Modelling the purchase propensity: analysis of a revolving store card

We investigate the incremental roles of information that becomes available only after a revolving loan has been granted in explaining and predicting the time taken until the borrower makes a second purchase. Using data relating to a store card, granted around the time of first purchase and used in Belgium, we find that characteristics of a first purchase and remaining credit available for use enhance the explanatory and predictive power of application characteristics. The relationship differs between good and poor payers.

Exploring Management Capability in SMEs using transactional data

Small- and medium-sized enterprises (SMEs) have become very important in most world economies. Governments have developed policies to support them and within the United Kingdom the government has encouraged lending to SMEs. Traditional relationship banking is based on the confidence a banker may have in the quality of SME’s management. Yet with a shift towards transactional quantitative risk assessment, there is a concern that Management Capability, which is critical to the success of a SME, is not necessarily captured by risk modelling. This paper reports findings from work on determining Management Capability from quantitative transactional measures. The study has used principal component analysis and partial least squares regression to elicit manifestations of Management Capability. The results indicate some success in determining measures for Management Capability.

Does benchmarking help

In this paper we examine benchmarking as it is used in fund management and especially asset allocation. We explore the concept of benchmarking in fund management, and selection of the appropriate benchmark. Some of the major problems associated with benchmarking are dealt with, including the risks involved and measures taken to deal with the inherent risk, such as risk adjustment. Finally we advocate that trustees need to interact with fund managers more closely if the fund is to develop in the desired direction. This should include an understanding of the organisational aspects of the fund managers role.

Exploring the performance of Small and Medium Sized Enterprises through the Credit Crunch

Small- and medium-sized enterprises (SMEs) are major contributors to most western economies. They are often supported by government policies, and in the UK the government encourages banks to lend to them. It is generally believed that the credit crunch has had an impact on the performance of SMEs. This study looks at the impact of the crunch using large samples from 2007 through to 2010. It looks at performance by region, age and industrial sector (SIC code). It then proceeds to explore the modelling of default over the years, with a focus on young businesses. It was found that there is a degree of stability within the models, though the level of default varies across years. Young businesses, as has been found before, are shown to be more vulnerable.

Monetary and Relative Scorecards to Assess Profits in Consumer Revolving Credit

This paper presents for the first time a relative profit measure for scoring purposes and compares results with those obtained from monetary scores. The suggested measure is the cumulative profit relative to the outstanding debt. It can also be interpreted as the percentage coverage against default. Monetary and relative measures are compared with both being estimated using direct and indirect methods. Direct scores are obtained from borrower attributes, while indirect scores are predicted using the estimated probabilities of default and repurchase. Results show that specific segments of customers are profitable in both monetary and relative terms. The best performing indirect models use the probabilities of default within 12 months on books. This agrees with existing banking practice of default estimation. Direct models outperform indirect models. Relative scores would be preferred under more conservative standpoints towards default because of unstable conditions and if the aim is to penetrate relatively unknown segments. Further ethical considerations justify their use in an inclusive lending context.