Turning Data into Actionable Business Impact with AI and Machine Learning

Agus Jamaludin, Deputy Data Science Manager, Petrosea

Agus Jamaludin is a Data Scientist Lead with a strong background in mathematics and analytics. He began his journey in data science after earning a Mathematics degree from UIN Sunan Gunung Djati Bandung, where he built a solid analytical foundation.

Jamaludin started his career as a Data Scientist at Ebdesk Malaysia Sdn Bhd, specializing in time series data analysis, text mining and NLP models for goods pricing, news and social media analytics. He then joined Hitachi Ebworx Sdn Bhd, focusing on customer behavior analytics for insurance approval and payslip data extraction using OCR.

In 2019, Agus returned to Indonesia as a Data Scientist at Metrodata Electronics, where he worked on various predictive modeling projects, including developing recommendation systems. Later that year, he joined Petrosea as a Senior Data Scientist and now leads a team of four. His expertise includes building predictive maintenance models, developing real-time data pipelines and designing Power BI dashboards to support strategic decision-making.

Passionate about AI and data-driven solutions, Jamaludin is dedicated to leveraging data science to create business impact while mentoring and developing future data science talent.

Through this article, Jamaludin emphasizes the critical role of AI and data analytics in optimizing operations and enhancing safety. It explores strategies to ensure reliable decision-making through advanced data pipelines and AI-powered solutions.

Optimizing Operations with AI and Machine Learning

As a Lead Data Scientist at Petrosea, my role is centered on data utilization, starting from building the data architecture and data pipeline, leveraging AI, machine learning and data analytics and building data reporting using bi tools to drive innovation and sustainability in the mining, engineering and construction sectors. By implementing data-driven solutions, we optimize operations, reduce costs and enhance efficiency while supporting environmental and safety initiatives.

“Builds AI-powered corrective action for inspection reports to improve safety monitoring and environmental compliance and builds AI-powered microcontroller unit data extraction”

One of my key contributions is to lead the development of data pipelines using Azure Data Factory (ADF), enabling faster and more accurate decision-making. This leads to developing an advanced data analytic model to optimize production by allocating the right number of trucks and shovels and monitoring the challenging route. Builds AI-powered corrective action for inspection reports to improve safety monitoring and environmental compliance and builds AI-Powerd microcontroller unit data extraction. Additionally, my team supports developing some data visualization, such as reporting for project readiness tracking to monitor the progress of preparation.

Ensuring Data Quality for Reliable Decision-Making

The main data challenges I face revolve around data integration, data quality and model deployment for improving operational efficiency and safety.

The operations rely on data from various sources, such as IoT sensors, fleet management systems, ERP and others. These systems often use different formats and update at different intervals, making integration complex. To tackle this challenge, I design and implement data pipelines using ADF to ensure seamless data ingestion and transformation. I centralize and structure the data, enabling smooth integration across departments.

Inconsistent or incomplete data can lead to incorrect insights, affecting operational efficiency and risk assessments. One of the challenges for Safety Monitoring is that when the operator does the inspection, there is some free text input that leads to typos, use of slang words, etc., making the data very noisy. To tackle this, I designed AI-powered corrective action recommendations to ensure that the operator inputs the right report, automatically classifies the report and gives the action recommendations.

By overcoming these challenges, I contribute to increasing operational efficiency and enhancing safety in mining operations.

Key Advice for Aspiring Leaders

To excel in data science, focus on strong fundamentals in mathematics, statistics and machine learning—understanding the “why” behind models is key. Business and domain knowledge are just as crucial; knowing engineering, mining or manufacturing workflows sets you apart. Storytelling and visualization skills help translate complex insights into actionable decisions for stakeholders. Automation and machine learning are essential for scaling AI solutions, so mastering CI or CD, data pipelines and containerization ensures production readiness. Stay resilient—real-world data is messy and failure is part of the process. Keep experimenting, learning from setbacks and refining your approach. Lastly, network and stay updated through conferences, hackathons, and online communities. The field evolves rapidly—adapt, innovate, and enjoy solving real-world problems with data!