Saima Absar

Data Scientist Chevron Phillips Chemical Company

Data Scientist with a PhD in Computer Engineering specializing in causal inference, deep learning, and time-series modeling. Experienced in designing state-of-the-art neural architectures and end-to-end ML pipelines, including real-time MLOps systems in Databricks, MLflow, and Seeq. Over five years of experience developing high-impact regression, classification, and forecasting models, translating research innovation into industrial-scale solutions and peer-reviewed publications.

Pre-Conference Workshop & Masterclass - February 23, 2026

1:30 PM Cause & Effect: Leveraging Causal AI to Streamline Frontline Processes

Having a holistic view of your assets and workflows is essential, but without understanding why things happen, how actionable are your insights?

Causal AI goes beyond traditional statistical correlations by identifying root causes and modelling interventions that can actively change outcomes, not just predict them. In dynamic energy environments, where frontline decisions impact safety, performance, and emissions, causal AI enables operators to simulate counterfactual scenarios (what would happen if a different action were taken?) and tailor workflows accordingly. This workshop will explore how causal AI can unlock real-time, decision-ready insights that drive measurable business value across operations.

In this workshop, we’ll explore:

Real-world use cases of causal AI in energy, from predicting and preventing equipment failure, to reducing emissions and mitigating performance degradation
Dynamic modelling of interactions between resource allocation, process variables, and field conditions, using causal graphs to tailor recommendations for frontline teams
Creating a feedback loop that continuously learns from operational data, enabling adaptive workflows and proactive interventions

Main Conference Day 1 - February 24, 2026

11:10 AM Panel Discussion: No Disconnects: Proving the Value of Machine Learning for Scalable Predictive Maintenance

As the industry seeks to move beyond reactive maintenance, machine learning offers a powerful opportunity to predict failures before they happen, reducing downtime, optimizing asset performance, and improving safety. This panel explores how early-stage pilots can lay the foundation for scalable, enterprise-wide predictive maintenance solutions.

How to build a business case for machine learning in maintenance by identifying high-value assets, leveraging historical failure data, and demonstrating early wins
Strategies for assessing data readiness and model adaptability, ensuring that predictive algorithms are trained on relevant, high-quality inputs and evolve with operational complexity
Stakeholder engagement techniques that drive adoption, from localized decision-making to cross-functional collaboration between data teams and asset owners
How proof-of-concept projects can be scaled across the enterprise with lessons learned in governance, infrastructure integration, and long-term value tracking

Check out the incredible speaker line-up to see who will be joining Saima.

Download The Latest Agenda

In Partnership With:

QUESTIONS?

Telephone: +1 813-658-2511
Email: enquire@iqpc.co.uk