Decision Models - NOTES

Decision Models

            Decision models describe the relationship between all the elements of a decision the known data (including results of predictive models), the decision and the forecast results of the decision in order to predict the results of decisions involving many variables. These models can be used in optimization, a data-driven approach to improving decision

logic that involves maximising certain outcomes while minimising others. Decision models are generally used offline, to develop decision logic or a set of business rules that will pràduce the desired action for every customer or circumstance.

            The basis of a decision model is to improve the outcome of some well defined business decision, taking into account multiple variables. This model uses well-known data (9ften included historical decision-making data), the business decision and the probability of some result based on the given variables or factors. The results of these models are often used to write business rules found in the line-of-business applications.

A decision model can be as simple as directing relevant information to appropriate decision-makers at the right time, i.e., a reporting rules system, in contrast to the information model which deals with the content of reports. A more complex decision model could trigger actions based on a rule-base consisting of a set of If... .THEN rules or a formal decision tree. However production rules and decision trees are mostly suited to highly structured, routine decisions. More sophisticated decision models could incorporate elements of the decision-making process such as support for collaborative decision-making.

            Business decisions take diverse forms. As one undertakes to build a predictive analytics model, he/she is concerned with two main types of decision:

1. Strategic Decisions: These decisions are often not well defined, and focus only on the big picture. Strategic decisions have an impact on the long-term performance of company and correlate directly with company’s mission and objectives. Senior managers are usually the ones who make strategic decisions.
2. Operational Decisions: These decisions focus on specific answers to existing problems and define specific future actions. Operational decisions usually do not require a manager’s approval, although they generally have a standard set of guidelines for the decisions-makers to reference.

            The two classes of decisions require different predictive analytics models. For example, the chief financial officer of a bank might use predictive analytics to gauge broad trends in the banking industry that require a company-wide response (strategic). A clerk in the same bank might use a predictive analytic model to determine creditworthiness of a particular customer who is requesting a loan (operational).

            With these two major types of decisions in mind, one can identify co-workers at company who make either operational or strategic decisions. Then can determine which type of decision is most in need of predictive analytics and design an appropriate prototype for model.

            Decision modelling is the most advanced form of business analytics. Decision models predict the outcomes of complex decisions for a business in much the same way that predictive models are used to predict consumer behaviour. The decision model first maps the relationships between all the elements of a decision:

1. Known data;
2. Decision one is considering making; and
3. Forecasted results of the decision (including results of predictive models).

            The decision model predicts what will happen to bottom-line profit if a given action is taken. One can then use these models to improve business’s performance by deriving decision strategies that find more favourable trade-offs among company’s key business objectives (e.g., if goal is to maximise revenue growth) while minimising losses and expenses. Optimisation is a mathematical process to find the best decision model strategy for a given business problem. Decision models are generally used to create decision strategies and business rules that are then automated via application software.