People / Students / Class of 2026
Luning Ding is a Master’s student in Machine Learning and Data Science at Northwestern University, building on her undergraduate degree in Statistics and Data Science from UCLA. She has worked across multiple industries, gaining hands-on experience through internships at TikTok, eBay, and Hundsun Technologies. At TikTok, she designed and evaluated large-scale A/B tests, developed causal inference frameworks, and built an AI attribution bot in Python and SQL that improved root cause detection efficiency by 50%. She also created monitoring dashboards to identify risky creators and detect GMV fluctuations, helping the platform strengthen content quality and product strategy. At eBay, Luning managed over a billion records of transaction and user data, built real-time dashboards with Tableau, and developed multidimensional data cubes for fashion product analysis, cutting data latency from 24 hours to under 1 hour and enabling faster insights for business teams. Earlier, as a Machine Learning Engineer Intern at Hundsun Technologies, she worked on OCR and text detection systems, improving model accuracy by nearly 10% through advanced non-maximum suppression and dynamic thresholding techniques. Beyond industry, Luning contributed to research at UC Santa Barbara, where she applied computer vision models like UNet and ResNet to study bee hair density, publishing her work in Functional Ecology. She is skilled in Python, SQL, R, and C++, with expertise in machine learning frameworks such as PyTorch and TensorFlow, and tools like Tableau and Excel. Her projects span predictive modeling, experiment design, causal inference, and computer vision, reflecting her passion for turning complex data into actionable insights. Outside of work, she enjoys exploring new technologies, sharing her projects on GitHub, and tackling problems that push the boundaries of machine learning and data science.
