Expert systems and evolutionary computing for financial investing: A review

Better safe than sorry: defensive loan assessment behaviour in a changing bank environment

“…Turning to the individual LO level, our results suggest that defensive loan assessment behaviour may occur because of difficulties to make sense of and transmit soft information, and a tendency to avoid situations where individual mistakes might occur. While these difficulties with soft information are firmly supported in previous financial sector research (Rada, 2008;Udell, 2008;Liberti & Mian, 2009) and in research from other contexts (e.g., Jönsson & Grönlund, 1988;McSweeney, 1996, Chua, 1996Boland & Schultze, 1996), our findings suggest that sensemaking difficulties may cause defensive loan assessment behaviour. The results also illustrate how an individual LO can be affected by "a slap on the wrist" from bank management or the credit committee.…”

“…Our results suggest that existing loan assessment routines begin with the use of hard information, which can be processed in the control and support system (cf. Rada, 2008;Udell, 2008; see also Boland, 1979). The LOs are accountable to the bank and the credit committee and may prefer to make their case concerning a loan application based on information which is perceived to be "factual" (e.g., McSweeney, 1996).…”

“…One approach to take is to devise control and support systems that signal when a loan application deviates from desired tolerances. When credit granting procedures are strongly regulated and standardized, LOs are expected to commence their assessment by processing information about the application through the control and support system used (Mahmoud et al, 2008;Rada, 2008). However, as suggested by Argyris (1977) and Jönsson and Grönlund (1988), the information processed in central control systems may contrast with information needs on a local level.…”

“…Control and support systems convey hard information within the banks' organisation (Rada, 2008;Udell, 2008), and structure the assessments made by the LOs (Kumra et al, 2006). The systems emphasize "facts" about the loan applicant (cf.…”

An adaptive neuro-fuzzy system for stock portfolio analysis

“…Rada 34 conducted a comprehensive literature review of expert systems, which have been applied in this certain area. Among all types of expert systems, neuro-fuzzy systems, specially ANFIS, have been widely used for financial time series prediction problems.…”