Validating Business Problem Hypotheses: A Goal-Oriented and Machine Learning-Based Approach

Validating an elicited problem to hinder a business goal is
often more important than nding solutions in general. For example, val-
idating the impact of a client's account balance toward an unpaid loan
would be critical as a bank can take some actions to mitigate the prob-
lem. However, business organizations face diculties conrming whether
some business events or phenomena are causing a problem against a busi-
ness goal. Some challenges to validate a problem are identifying testable
factors for the identied problem, preparing data to validate, analyzing
relationships between the factors and a problem, and reasoning the re-
lationships towards high-level problems. Information systems developed
to solve unconrmed problems frequently tackle an erroneous problem,
leading to some dissatisfying systems, consequently not achieving busi-
ness goals. This paper proposes a goal-oriented and machine learning-
based approach, Gomphy, for validating a business problem. The Gom-
phy presents an ontology and a process, a problem-related entity model-
ing method to identify relevant data features, a data preparation method,
and an evaluation method of a problem for high-level problems. To illus-
trate our approach, we have validated problems behind an unpaid loan
in one bank as an empirical study. We feel that at least the proposed ap-
proach helps validate business events negatively contributing to a goal,
giving some insights about the validated problem.