Artificial Intelligence for Intelligent Forecasting in Project Time Estimation

School of Defence Technology and Management, Defence Institute of Advanced Technology, Pune, India

^* Corresponding author: This email address is being protected from spambots. You need JavaScript enabled to view it.

Published online: 29 May 2026

Abstract

Successful project execution requires managing the three main constraints - scope, cost, and schedule - throughout its life cycle. Among these, scheduling is particularly difficult in research and development environments because of the unpredictable nature of activities. To address this challenge, an accurate duration prediction becomes essential. The conventional approaches fail to address the complexity of Research & Development projects and there's a need for technologies like Artificial Intelligence (AI) which helps to strengthen the forecasting accuracy. In this study, the PRISMA framework is employed to analyses systematically how these methods using AI can contribute to estimate project timelines. Comparative Performance of different AI techniques across various industries have been studied in this review mainly focusing on the improvement of the accuracy of time predictions in R&D projects. A total of 354 publications were selected which offered insights into the various models used and evaluated their performance with respect to parameters like Mean Square Error (MSE) and Mean Absolute Error (MAE). Based on the synthesized results, research gaps and future opportunities were identified. The results revealed that only limited research addresses the timeline predictions using AI approaches. Deep learning (DL) and Machine Learning (ML) models demonstrated prediction accuracies as 92% and 80% reduction in errors as compared to the conventional methods like Earned Value Management (EVM) and Earned Schedule Management (ESM). Based on these results, it is suggested that modern AI-based systems can give better prediction on timelines of project and thus helping the project managers with more reliable instruments for planning, resource distribution, and managing uncertainties in complex projects.