Open to opportunities

Phil Xia

@philxia

Message

Data scientist specializing in machine learning and statistical analysis.

Netherlands

Message

What I'm looking for

I am seeking a collaborative environment that fosters innovation and growth, where I can leverage my data science skills to drive impactful projects.

I am a dedicated data scientist with a strong foundation in machine learning and statistical analysis, honed through rigorous academic training and hands-on experience in diverse roles. My journey began with a Bachelor's degree in Electrical Engineering from Xi'an Technological University, followed by a Master's degree in Artificial Intelligence from Leiden University. This educational background has equipped me with the technical skills necessary to tackle complex data challenges.

In my recent role as an Analytics Engineer at The Hague Tech, I successfully conducted statistical analyses and model evaluations that led to a remarkable 93% accuracy in classification algorithms. My ability to develop comprehensive feature engineering pipelines significantly reduced model training time by 78%. Additionally, my experience as a Research Data Scientist at Randstad allowed me to design end-to-end machine learning workflows, improving model interpretability by 30% through custom evaluation metrics.

Throughout my career, I have demonstrated a commitment to excellence and innovation, as evidenced by my successful projects, including a credit fraud scorecard model and a BERT-based text classification system. I thrive in environments that challenge my analytical skills and allow me to contribute to impactful data-driven decisions.

Experience

Work history, roles, and key accomplishments

Analytics Engineer

The Hague Tech

Nov 2024 - Apr 2025 (5 months)

Conducted rigorous statistical analysis and model evaluation for classification algorithms, implementing parameter optimization techniques that achieved 93% accuracy through meticulous experimental design. Developed comprehensive feature engineering pipeline using scikit-learn and pandas, reducing model training time by 78% through statistical preprocessing and dimensionality reduction techniques.

Statistical Analysis Model Evaluation Classification scikit learn Pandas Dimension Reduction Technical Documentation

Research Data Scientist

Randstad

Nov 2023 - Aug 2024 (9 months)

Designed end-to-end machine learning workflow using Python, Jupyter notebooks and TensorFlow, developing custom evaluation metrics that improved model interpretability by 30%. Conducted exploratory data analysis and statistical inference on large datasets using SQL and pandas, identifying key patterns that informed feature selection and model development.

Machine Learning Workflows Python Jupyter Notebooks TensorFlow SQL Pandas A B Testing

Data Scientist

Yijie Tech

Oct 2020 - May 2022 (1 year 7 months)

Led data preprocessing and feature selection efforts using PCA and other statistical techniques, identifying 15 critical predictors from 200+ variables while preserving 94% of variance. Designed and executed causal inference studies using statistical models to evaluate intervention effects, developing methodologies that provided robust estimates with quantifiable confidence intervals.

data preprocessing Statistical Techniques Causal Inference Statistical Modeling PyTorch Model Evaluation