Pablo Pytel

Feasibility and effort estimation models for medium and small size information mining projects

Abstract Information mining is a sub-discipline of Information Systems which provides the non-trivial knowledge needed for making decisions inside an organization. Although such projects have different features from Software Engineering ones, they share some of their problems. Among these problems two are highlighted: unmanaged risks and inaccurate estimations of necessary resources to complete the project. In this context, this paper presents two ad-hoc models to be applied in Small and Medium-sized Enterprises: one for assessing project feasibility and the other for estimating the resources and time required to carry out the project. Both models should be applied at the beginning of the project.

A Proposal of Effort Estimation Method for Information Mining Projects Oriented to SMEs

Software projects need to predict the cost and effort with its associated quantity of resources at the beginning of every project. Information Mining projects are not an exception to this requirement, particularly when they are required by Small and Medium-sized Enterprises (SMEs). An existing Information Mining projects estimation method is not reliable for small-sized projects because it tends to overestimates the estimated efforts. Therefore, considering the characteristics of these projects developed with the CRISP-DM methodology, an estimation method oriented to SMEs is proposed in this paper. First, the main features of SMEs’ projects are described and applied as cost drivers of the new method with the corresponding formula. Then this is validated by comparing its results to the existing estimation method using SMEs real projects. As a result, it can be seen that the proposed method produces a more accurate estimation than the existing estimation method for small-sized projects.

Evaluation of the Bias of Student Performance Data with Assistance of Expert Teacher

Machine Learning algorithms have many advantages and a great potential for solving complex problems in different domains. However, it is not “magical”. One of its main difficulties lies in recollecting representative data of the domain in order to train the system, otherwise, its efficacy will be seriously compromised. Therefore, a method has been proposed to evaluate the collected data with the assistance of the available domain experts and determine whether it can be used. In this work, the method is applied to evaluate two versions of data gathered on the students’ performance in an undergraduate program course. As a result, it is determined whether they can be used in the training of an Intelligent System that will foretell such performance.