Xiaochuan’s blog
about
fisrt principles first
Categories
All
(11)
applied probability
(1)
credit risk
(2)
data engineering
(1)
deep learning
(2)
hacks
(2)
kaggle
(1)
machine learning
(4)
python
(7)
time series
(1)
Financial time series: a journey from code to maths, and back
time series
python
In this post we discuss a fundamental model in financial time series modelling - the ARCH model.
Oct 15, 2024
Xiaochuan Yang
Git 101
hacks
Using git to manage text files (e.g. code files) is inevitable for keeping track of all changes while developing and maintaining a project.
Apr 13, 2024
Xiaochuan Yang
Learn transformer with makemore and torch
deep learning
python
[last modified on 2024-03-22]
Feb 16, 2024
Xiaochuan Yang
SQL 101
data engineering
Every professional interacting with data will come across SQL sooner or later. In this post, we cover a core set of vocabulary, grammer, expression for efficient use of this…
Jan 27, 2024
Xiaochuan Yang
What is required to achieve a top 20% ranking in Kaggle playground series
kaggle
python
machine learning
The playground series is devoted to tabular datasets and are the most accessible competitions for beginners to learn and develop skills. This blog/notebook is to showcase…
Dec 16, 2023
Xiaochuan Yang
bits of fastai live-coding sessions
hacks
Jeremy Howard, the founder of fastai, organized a series of live coding sessions covering the basics of git, bash, vim, tmux, and more, as a companion to the free fastai…
Nov 11, 2023
Xiaochuan Yang
Machine Learning Recap 1 Concepts
python
machine learning
In a supervised learning, we specify
Oct 27, 2023
Xiaochuan Yang
Credit Risk Models Ep 2 machine learning methods for parameter estimation
credit risk
python
machine learning
In a previous post, we’ve modelled the loss of a portfolio of
\(d\)
instruments as follows
\[ L = \sum_{i=1}^d \mu_i S_i I_i, \]
where
\(L\)
represents the total loss,
\(\mu_…
Oct 20, 2023
Xiaochuan Yang
Credit Risk Models Ep 1 Fundamentals
credit risk
applied probability
python
This is the first post in a series dedicated to credit risk models. The model discussed in this post is intentionally naive, as it relies on several unrealistic assumptions…
Oct 15, 2023
Xiaochuan Yang
Understanding Machine Learning: a series of 20 videos
machine learning
From Oct 2022 to Feb 2023, I have created a series of 20 videos (in Chinese) on machine learning theory and algorithms on bilibili.com, closely following the excellent…
Oct 14, 2023
Xiaochuan Yang
Secret ‘SAWS’ of deep learning, feature backprop
deep learning
python
My colleague Simon Shaw came up with the memorable notation SAWS for the key recursion step in backprop in a Year 2 module on deep learning. I found this a perfect example…
Oct 10, 2023
Xiaochuan Yang
No matching items