1887

Abstract

Summary

Despite the promising potential of machine learning (ML) and advanced analytics, the journey from development to production in industrial settings is fraught with challenges. According to reports by Gartner and Harvard Business Review, up to 85% of AI and ML projects fail to deliver on their promises. A variety of industrial case studies have been conducted to get to the root causes of failure and identify avenues to ensure success.

This work adds to this corpus of experience by cataloguing insights and the nuances of learnings to date on bp’s journey to advance its technology in predictive analytics and apply ML and advanced analytics.

Leveraging practical implementation experience, it has been found that successful deployment and operations of ML and advanced analytics, 1) begins with understanding the ecosystem of technologies available to address a business problem, 2) requires deep collaboration between operations subject matter experts (SMEs) and skilled data scientists, and 3) requires a means to deploy and maintain models/ analytics in a production setting.

This work outlines a proprietary framework called ‘ForeSite’, which has leveraged these insights and is delivering this technology to bp’s P&O business: it delivers “foresight for site”.

© EAGE Publications BV
Loading

Article metrics loading...

/content/papers/10.3997/2214-4609.202539097
2025-03-24
2026-02-08

  • From This Site

    /content/papers/10.3997/2214-4609.202539097
    dcterms_title,dcterms_subject,pub_keyword
    -contentType:Journal -contentType:Contributor -contentType:Concept -contentType:Institution
    10
    5
Loading full text...

Full text loading...

References

  1. BOJINOV, I. [2023] Keep Your AI Projects on Track. Published report. https://hbr.org/2023/11/keep-your-ai-projects-on-track
     [Google Scholar]
  2. GARTNER, INC. [2019] 4 Types of Analytical Tools to Support Insight Generation. Published report. http://www.gartner.com/en/documents/3898666/4-types-of-analytical-tools-to-support-insight-generatio
     [Google Scholar]
  3. LU, E. [2024] Why Do AI Projects Fail? Published report. https://towardsdatascience.com/why-do-ai-proiects-fail-9b07f32ce321
     [Google Scholar]
  4. MASCI, J. [2022] AI Has a Poor Track Record, Unless You Clearly Understand What You’re Going for. Published report. https://www.industryweek.com/technology-and-iiot/emerging-technologies/article/21214523/ai-has-a-poor-track-record-unless-you-clearly-understand-what-youre-going-for
     [Google Scholar]
  5. PALEYES, A., URMA, R, LAWRENCE, N.D. [2022] Challenges in Deploying Machine Learning: A Survey of Case Studies. ACM Comput. Surv.55, 6, Article 114. https://doi.org/10.1145/3533378
     [Google Scholar]
  6. RYSEFF, J., DE BRUHL, B.F., NEWBERRY, S.J. [2024] The Root Causes of Failure for Artificial Intelligence Projects and How They Can Succeed. Published report. https://www.rand.org/pubs/research_reports/RRA2680-1.html
     [Google Scholar]
  7. SINHA, S., LEE, Y.M. [2024] Challenges with developing and deploying AI models and applications in industrial systems. Discov Artif Intell4, 55. https://doi.org/10.1007/s44163-024-00151-2
     [Google Scholar]
  8. WESTENBERGER, J., SCHULER, K., SCHLEGEL, D. [2022] Failure of AI projects: understanding the critical factors. Procedia Computer Science196. https://doi.org/10.1016/j.procs.2021.11.074
     [Google Scholar]
/content/papers/10.3997/2214-4609.202539097
Loading
Insights into Predictive Analytics Deployment and Operations
Conference Proceedings 2025, 1 (2025); https://doi.org/10.3997/2214-4609.202539097
/content/papers/10.3997/2214-4609.202539097
/content/papers/10.3997/2214-4609.202539097
Loading

Data & Media loading...

Most Cited This Month Most Cited RSS feed

This is a required field
Please enter a valid email address
Approval was a Success
Invalid data
An Error Occurred
Approval was partially successful, following selected items could not be processed due to error