By Ololade Emmanuel-Macaulay

Quality assurance and compliance outcomes are very key in the manufacturing and financial sectors.

In this interview with Ololade Emmanuel-Macaulay, Quality Assurance Auditor and Compliance expert Abiola Olanike Olawore breaks down how to use data analytics and predictive modelling to drive quality assurance.

Excerpts:

 You’ve led quality and compliance efforts across the manufacturing and banking industries—very different operational environments. Let’s start with a central theme in your work. How have you leveraged data analytics to improve quality assurance outcomes?

 Thank you for having me. At the heart of my work is a commitment to data-driven quality assurance. Regardless of the sector, whether in manufacturing or financial services, the goal remains to reduce risk, improve process efficiency, and ensure compliance. During my time at Xerox Henry Stevenson, we implemented predictive analytics models to monitor product defects and customer satisfaction in real-time. By integrating Python for automation, statistical process control tools, and Power BI for visualization, we improved defect resolution rates by 50% and raised customer satisfaction by 25%. These outcomes directly supported our ISO 9001 and GMP compliance mandates, emphasizing continuous improvement and objective decision-making based on data.

That’s impressive. Could you walk us through a specific case where predictive modeling made a significant impact?

Absolutely. In 2022, we faced a consistent non-conformance pattern in our Xerox production process. I led a cross-functional task force to apply regression models and Six Sigma principles. Using Tableau, we visualized key patterns and uncovered bottlenecks in real-time production data. By acting on those insights, we reduced non-conformities by 40%, translating into a cost savings of about $1.5 million annually. That project wasn’t just about fixing a process but embedding a culture of precision, accountability, and prevention.

Beyond manufacturing, how did you apply these analytical techniques in financial services?

My time at Guaranty Trust Bank allowed me to translate these methods into the financial world. We developed a fraud detection system by integrating machine learning tools and SQL-based dashboards. These systems flagged transactional outliers and automated quality testing, which reduced manual reporting errors by 35% and helped us safeguard over $5 million in potential fraud exposure. More importantly, it is aligned with regulatory mandates and internal control frameworks essential to maintaining financial integrity. It demonstrated how predictive modeling could effectively serve compliance and risk mitigation functions.

Let’s shift to tools. Power BI seems to have played a recurring role in your QA strategy. How does it support real-time monitoring and compliance?

 Power BI has been instrumental in translating raw data into actionable insights. I designed dashboards that displayed real-time non-conformance trends, supplier performance metrics, and audit turnaround timelines. One key use case involved integrating CAPA (Corrective and Preventive Action) tracking into the dashboards. This concept enabled leadership to intervene quickly and shortened remediation timelines by 30%. In quality control, real-time visibility isn’t just convenient—it’s critical. It allows us to respond proactively instead of reactively, which is vital in regulated environments.

And what about automation—what role does it play in predictive analytics and regulatory compliance?

Automation is foundational to modern QA. At Xerox, I collaborated with our IT team to develop automated compliance tracking systems using Python scripts. These systems not only flagged data anomalies but also generated automated reports, which reduced reporting errors by 40% and saved about $1.1 million annually. We also embedded these automation frameworks into our internal and external audit preparation workflows. This action helped us align with statistical process control, sampling protocols, and audit readiness standards, ensuring we’re always a step ahead.

How do you ensure collaboration across departments with such complex systems in place?

 Cross-functional collaboration is key to long-term success. I led initiatives that brought together quality, production, IT, and compliance teams. We created shared SOPs and developed risk-based inspection frameworks that everyone could understand and use. I also facilitated training workshops focused on data literacy, which allowed non-technical staff to interpret performance metrics confidently. This inclusivity was critical in fostering a culture of collective accountability, which, in turn, improved overall process capability and reduced variation in outcomes.

Your work at Xerox and GTBank has pushed the boundaries of traditional QA. How has artificial intelligence (AI) transformed how you approach audits and risk management?

AI has fundamentally changed how we approach quality—turning audits from reactive checks into proactive risk management tools. At GTBank, for example, we used machine learning models to detect fraudulent transaction patterns, leading to a 20% drop in fraud-related activity and saving the bank $5 million. At Xerox, we used Python-powered predictive analytics to forecast defect trends before they occurred on the production line. These technologies align with ISO 9001’s emphasis on evidence-based decision-making and continuous improvement, elevating compliance from a requirement to a strategic capability.

That’s a strong statement. But what about transparency—especially with regulators concerned about “black box” models?

A valid concern. We’ve addressed this using SHAP (Shapley Additive Explanations) to make our AI models interpretable. For instance, in GTBank’s fraud detection system, SHAP allowed us to pinpoint specific features like transaction amount or timing that influenced the model’s decision. Pairing this with interactive Tableau dashboards meant we could communicate risk indicators to regulators. It ensured transparency and kept us compliant without compromising on innovation.

 Let’s talk about methodology. How have you applied Agile practices within regulated QA environments?

We pioneered an Agile-Six Sigma hybrid model at Xerox. Instead of waiting for quarterly audits, we used Agile sprints to test compliance controls incrementally. This approach reduced our audit turnaround time by 30%. One innovation we introduced was using blockchain to log supplier quality data, which created tamper-proof records for FDA and ISO audits. Agile empowered us to adapt quickly to regulatory changes like GDPR without operational disruption.

Your CV mentions $1.5M in savings through automated compliance tracking. How does this tie into Xerox’s technology strategy?

That initiative directly supported Xerox’s focus on technology-driven process optimization. We automated 80% of ISO 9001 documentation checks using RPA bots, cutting manual errors by 40%. Then, we layered that with Power BI dashboards to visualize KPI trends and feed directly into our CAPA processes. It allowed us to shift from lagging indicators to leading indicators, accelerating audits and driving $1.1M in additional operational efficiency annually.

Cybersecurity is a growing QA concern. How do you mitigate risks, especially when integrating AI?

 We take a proactive approach. At GTBank, for example, we embedded NIST cybersecurity frameworks into our QA tools. I trained our AI models on encrypted datasets and used Azure’s security protocols for breach detection. I conducted regular penetration testing to assess vulnerabilities. These practices helped reduce cyber-related QA risks by 30% and ensured compliance with ISO 27001 standards.

That’s reassuring. How do you ensure QA tools remain accessible to non-technical team members?

 Usability is non-negotiable. At Xerox, we designed training programs that empowered staff—regardless of technical background—to interpret Power BI dashboards confidently. We even used gamified modules to boost engagement, which improved defect reporting rates by 35%. Making tools accessible is not just a training issue—it’s a cultural one. When everyone understands the data, everyone becomes a stakeholder in quality.

Before we wrap up, what’s next for QA? Are you exploring any new frontiers?

Definitely. We’re piloting Natural Language Processing (NLP) models to scan regulatory updates and auto-update SOPs. There’s also enormous potential in quantum computing for supply chain optimization. Regardless of the technology, the core principle remains the same: quality assurance is about safeguarding trust. The future lies in striking the right balance between innovation and human judgment.

Lastly, what’s your vision for the future of quality assurance?

 I envision a world where QA isn’t confined to compliance checklists but is embedded into the DNA of strategic decision-making. Quality professionals will evolve into hybrid analysts and compliance stewards, using data to guide operational foresight. With the rise of AI, ethical auditing and data governance will become paramount. The goal is not just to meet today’s standards but to build resilient systems that can adapt, predict, and lead in the future. In essence, we must marry innovation with integrity to ensure that quality is controlled and future-proofed.

That’s a powerful note to end on. Thank you, Ms. Olawore, for sharing such profound insights. Your work exemplifies how data, combined with purpose and leadership, can transform quality assurance into a cornerstone of organizational excellence.

 Thank you. It’s been a pleasure to share my journey.