About

Welcome to my tech blog!

Short Bio

As a data scientist, I focus on building data science products. For modeling, I often utilise regression (linear, logistic, spline), deep learning (word2vec, DeepWalk, wide & deep, transfer learning), ensemble methods (random forest, gradient boosting, stacking), factorization machines, and Apache Spark’s MLlib, depending on the use case. For deployment, I utilize a collection of other technologies such as Airflow, Jenkins, Kubernetes, MLflow, Spring Boot, Docker, and Git, among others. I am experienced in using both Amazon Web Services (AWS) and Google Cloud Platform (GCP).

As an investor, I manage money by investing across global equities, bonds, commodities, and foreign currencies. I focus on both strategic asset allocation and tactical asset allocation. To date, I have achieved an annualized time-weighted total return of 8.48% since inception in July 2016. To view my investment performance in more detail, feel free to click on the investments section.

Academically, I am trained in Statistics and Finance at NUS and NTU, respectively.

I am a Singapore citizen based in Singapore.

If you need help in building data science products, or struggle to understand investments and personal finance, feel free to reach out to me.

Skills

  • Favourite machine learning frameworks: Statsmodels, Scikit-learn, Keras, Tensorflow, XGBoost, LightGBM, Catboost, xLearn
  • Business applications: recommendation systems, search ranking, assortment optimisation, segmentation, churn analysis, leads optimisation, budget allocation
  • Programming Languages: Python, SQL, Java, R, Bash
  • Compute Instance: AWS EC2, Google Compute Engine
  • Data Warehouse (OLAP): Hive, Vertica, Presto, AWS Redshift, Google BigQuery
  • Database (OLTP): Oracle Database, LevelDB, Google Cloud SQL
  • Cloud Storage: AWS S3, Google Cloud Storage
  • Distributed Machine Learning: AWS EMR, Spark
  • Container Platform: Docker
  • Search Engine: Elasticsearch
  • Job Scheduler: AWS Batch, Airflow, Cron
  • CICD: Bitbucket Pipelines
  • Experimentation: MLflow
  • Visualisation: Tableau, Matplotlib
  • Version Control: Git, Bitbucket
  • Project Tracking: Jira, Asana, Trello
  • Financial statement analysis
  • Macroeconomics analysis

Contact Me

Feel free to contact me on LinkedIn for anything related to data science, investments, or start-up ideas!