date_range 11/03/2023 21:48

I have been working in the machine learning and data science (ML/DS) engineering area in industry for a year. Also, I had worked in the software engineering (SE) area for two years before this. Some of the SE experience could be shifted to ML/DS, but most of them are totally not transferrable. Here are my personal persepctives.

date_range 04/03/2023 22:30

Recently, we have done a project with xgboost model for classification. With the increasing of large amouts of data, we need to use XGBoost distributed training to replace the current pandas XGBoost training solution in Spark.

date_range 20/11/2022 00:30

Here we summarize a paper from “Predictive Model Performance: Offline and Online Evaluations” from Microsoft. It analyzes the offline and online metric discrepancy problem, and the simulated metric for simulating online performance.

date_range 06/11/2022 00:30

Here we introduce a paper from Facebook about ads click through rate prediction. It was an old paper published in 2014, but I believe it still has lots of good practices which we could learn from for ads service.

date_range 29/10/2022 21:30

Here we introduce Gmail’s Smart Compose which provides real-time and interactive writing suggestions. It is a large-scale neural language mode of sequence prediction. We use the question-answer format here.