Daniel Savu is a dedicated Senior Data Analyst at CMSPI, where he leverages his expertise in machine learning and data analytics to drive innovative solutions in the payments industry. With a strong focus on interpretable machine learning, Daniel is committed to building trust in AI...
Daniel Savu is a dedicated Senior Data Analyst at CMSPI, where he leverages his expertise in machine learning and data analytics to drive innovative solutions in the payments industry. With a strong focus on interpretable machine learning, Daniel is committed to building trust in AI systems, ensuring that stakeholders can understand and rely on the insights generated by complex algorithms.
In his current role, Daniel has successfully developed a sophisticated benchmarking solution utilizing the inTrees method in PySpark. This solution is instrumental in detecting false negative transactions, enabling CMSPI to enhance its fraud detection capabilities and provide actionable recommendations to clients. His proficiency in managing the entire machine learning model life-cycle—from feature engineering and modeling to deployment and monitoring—has been pivotal in aligning data-driven insights with the product roadmap.
Daniel's collaborative spirit shines through in his work on automated solutions for big data challenges, where he partners with cross-functional teams to streamline processes and improve operational efficiency. His technical skill set is robust, encompassing a variety of programming languages and tools, including Python, SQL, TensorFlow, and Azure Databricks, which he adeptly employs to extract meaningful insights from large datasets.
By combining his analytical prowess with a passion for advancing machine learning methodologies, Daniel Savu is not only enhancing the capabilities of CMSPI but also contributing to the broader conversation around responsible AI and its application in the financial sector. His work exemplifies the intersection of technology and trust, positioning him as a key player in the evolution of data analytics within the payments landscape.
