Daniel Hartley

Dynamic Data Scientist. Skilled in advanced analytics, machine learning, and predictive modeling with 8 years of expertise in Python, R, and deep learning frameworks. With a Master's from UC San Diego and a robust background spanning Charter Communications, CableLabs/Upramp, and the National Renewable Energy Laboratory. Strengths include EDA for use by technical and non-technical personnel, transforming complex data into actionable insights, and a passion for continued learning.

I’m a Data Scientist with 8 years of experience building scalable machine learning solutions and translating complex data into real-world impact. My journey has taken me from major telecoms to research labs, startups, and most recently, immersive tech—where I’m combining my passion for data with cutting-edge tools like full-body motion capture and VR.

At WIND, I’ve built systems to process high-dimensional positional data in real-time, optimized VR hardware/software integration, and developed live audience polling tools for large-scale events. My work here bridges hardware and software, pushing performance boundaries in immersive environments.

At Charter Communications, I developed a CNN that predicted Set Top Box failures with 96% accuracy, significantly improving system reliability. I’ve also worked with CableLabs and NREL, where I applied clustering, predictive modeling, and data transformation to optimize operations and enable better decision-making.

In a separate research-driven project, I collaborated on the development of a neural network Trojan detection model—reducing prediction time from 36 hours to just 3 through advanced feature reduction and architecture-agnostic modeling.

Across roles, I’ve consistently delivered insights that balance deep technical rigor with practical application. I’m always looking to solve interesting problems, build resilient systems, and collaborate with teams at the intersection of innovation and execution.

UC San Diego – MAS in Data Science (2021–2023)

I completed my Master of Advanced Studies in Data Science at UC San Diego's Jacobs School of Engineering, where I deepened my technical foundation in machine learning, statistical modeling, and large-scale data systems.

Throughout the program, I worked on real-world projects that emphasized both theory and application—from building predictive models and optimizing algorithms to exploring deep learning architectures and natural language processing. The curriculum challenged me to think critically about data pipelines, ethical AI, and scalable deployment strategies.

What stood out most was the program’s emphasis on collaboration and impact. Whether I was tuning hyperparameters, developing time-series models, or presenting results to different teams, the experience prepared me to turn raw data into meaningful insight in fast-paced environments.