Title: Kairós: using context histories for predictions and recommendations in projects time management

Authors: Felipe Chaves Rodrigues; Alexsandro Souza Filippetto; Robson Kerschner De Lima; Wesllei Felipe Heckler; Jorge Luis Victória Barbosa

Addresses: Applied Computing Graduate Program, University of Vale do Rio dos Sinos (UNISINOS), Av. Unisinos, 950 – São Leopoldo, RS, Brazil ' Applied Computing Graduate Program, University of Vale do Rio dos Sinos (UNISINOS), Av. Unisinos, 950 – São Leopoldo, RS, Brazil ' Applied Computing Graduate Program, University of Vale do Rio dos Sinos (UNISINOS), Av. Unisinos, 950 – São Leopoldo, RS, Brazil ' Applied Computing Graduate Program, University of Vale do Rio dos Sinos (UNISINOS), Av. Unisinos, 950 – São Leopoldo, RS, Brazil ' Applied Computing Graduate Program, University of Vale do Rio dos Sinos (UNISINOS), Av. Unisinos, 950 – São Leopoldo, RS, Brazil

Abstract: Time management is an important part of a project. Cost and quality are directly affected by any changes in deadlines. Therefore, this paper presents Kairós, a computational model for prediction and recommendation in project schedules. We made a systematic mapping study on the research topics, and the gaps found were the base for the creation of the model. The model makes recommendations to the manager proactively according to best practices in project management, learning with the approval or rejection of each recommendation. We performed an evaluation through a prototype using simulated use cases with real data from a software development company. The results showed that the model was able to predict with a precision of 94% whether a task would be completed with delay, with 86% accuracy. The results demonstrated that the use of context histories contributes to project management.

Keywords: project management; time management; project schedules; prediction; recommendation; context histories.

DOI: 10.1504/IJASM.2022.124168

International Journal of Agile Systems and Management, 2022 Vol.15 No.1, pp.31 - 52

Received: 02 Jan 2021
Accepted: 13 Jul 2021
Published online: 15 Jul 2022 *

Full-text access for editors Full-text access for subscribers Purchase this article Comment on this article