Fuzzy Application Library/Business and Finance Applications/Other Finance Applications

The other finance application papers on this site gave you in-depth coverage of a number of successful applications of fuzzy logic in finance. Many others do exist, however, not many practical applications have been published. This paper contains brief abstracts on other business applications using fuzzy logic. References have been included where applicable in order that you may obtain the full article.

Investor Classification

Many investment houses classify both their customers and their investments into three groups denoting their risk mentality:

• conservative and security-oriented (risk shy),
• growth-oriented and dynamic (risk neutral), and
• chance-oriented and progressive (risk happy).

To analyze how well a customer fits into these three groups, an investment house has designed a questionnaire with about two dozen questions that each have to be answered with values from 1 to 5. The questions range from personal background (age, martial state, number of children, job type, education type, etc.) to what the customer expects from an investment (capital protection, tax shelter, liquid assets, etc.). A fuzzy logic system was designed for the evaluation of the answers to the questions. The application is not published.

Insider Trading Surveillance

A system to automatically detect insider dealing and market manipulation using a combination of fuzzy logic, neural nets, and genetic algorithms has been developed for the London Stock Exchange [1]. The aim of the system is to detect rings of several individuals, or one individual with several accounts. The problem, which is extremely difficult to solve using conventional techniques, involves spotting the "signature" of certain traders from a vast amount of electronic camouflage.

Foreign Exchange Trading

In Japan, fuzzy logic is used in a foreign exchange trading system to predict the Yen-Dollar exchange rate [2]. The system uses fuzzy logic rules to make inferences based on economic news events that may affect the currency market. This news is "translated" into the fuzzy logic system’s input format by domain experts.

Cash Supply OptimizationFor banks with a large number of local branches and automated teller machines (ATMs), the supply of cash held involves costs. These costs are mostly due to the capital binding in the cash bills. Although it sounds odd at a first glance, cash is bound capital because it is money that cannot be used while it is stored in the form of bills waiting in a branch or ATM to be withdrawn by a customer. Hence, a bank can save a considerable amount of money if the total amount of cash can be reduced in its branches and ATMs. Conventionally, this problem is solved by bankers that assess the minimum amount of cash for each branch and ATM. However, the amount of cash required at the outlets will vary over time. First because of seasonal reasons, the necessary amount of cash will change over the week and the year differently for each branch and ATM. Second, the environment of the individual branches and ATMs changes over time. For example, new shops may open in the vicinity of a branch or a new office of another bank may open nearby. Hence, a one-time definition of a minimum cash amount for each branch and ATM by a banker will become obsolete and, hence, the average minimum amount of cash held in each branch and ATM can become larger than actually required. In a project of a European bank, fuzzy logic was used to recompute the minimum cash amount of each branch and ATM daily. This fuzzy logic system contained the expertise of the bankers for assessing the required lowest cash amount on the basis of the past cash flow of the branches and ATMs as well as a classification of their neighborhood. The system was able to reduce the average cash supply in the branches and ATMs by 7.1% without increasing the rate of situations where the branch or ATM ran out of cash. For a bank with about 450 branches and 1270 ATMs, this results in an average total of $3.8M less in cash supply.

Literature