STATISTICAL ANALYSIS OF TIME ESTIMATION PATTERNS IN AI PROJECT TIMELINES

Abstract

Accurate time estimation is always a challenge for AI projects due to their inherent complexities and innovative nature. This study examines patterns in time estimations across various AI projects, leveraging statistical methods to identify trends and challenges. A comparison with norms from non-AI projects reveals that AI projects exhibit significantly higher variability and underestimation rates. This research underscores the need for domain-specific frameworks and provides actionable recommendations for improving time estimation accuracy in AI development. Future directions include the collection of additional data and the development of automated tools for dynamic estimations.

References

1. Molokken, K., & Jorgensen, M. (2003). A review of surveys on software effort estimation. Proceedings of the 2003 International Symposium on Empirical Software Engineering, 223-230. https://doi.org/10.1109/ISESE.2003.1237981
2. Boehm, B. (1988). A spiral model of software development and enhancement. ACM SIGSOFT Software Engineering Notes, 11(4), 14-24. https://doi.org/10.1145/12944.12948
3. Kitchenham, B., et al. (2014). Evidence-based software engineering and systematic reviews. CRC Press. https://doi.org/10.1201/b17383