As I sit here with a fresh pile of snow being dumped on Toronto I realised that most of my recent posts have been a little light on markets and a little heavy on machine learning. I am reluctant to let all those efforts go to waste so I thought we can use some of … More Replicating GS-EQMOVE Model
In a previous post I discussed k-means clustering, which is a type of unsupervised learning method. Today I want to add another tool to our modeling kit by discussing hierarchical clustering methods and their implementation in R. As in the k-means clustering post I will discuss the issue of clustering countries based on macro data. … More Hierarchical Clustering
In my last post I discussed the importance of using a regularized classifier to avoid overfitting the data. I used contour plots to show the distortions in the decision boundaries of a logistic regression classifier on artificial data. Recently I have been going through Nigel Lewis’ “Build Your Own Neural Network Today!” and decided to … More Regularized Neural Network in R
I recently went through a Coursera course on Classification taught by Carlos Guestrin from U of Washington and thought it was excellent. There was an interesting discussion on model overfitting that I thought I would share. In previous posts I discussed linear models with shrinkage parameters such us ridge and lasso regression models. Similar approach … More Shaving a Classifier with Occam’s Razor
My posts have been spars as I adjust being back home. Today’s post will be about a somewhat gimmicky approach to visualizing correlation in the markets. A while back I came across an interesting article by Resovsky et al on minimum spanning trees. I do not have a background in graph theory but I have … More Minimum Spanning Trees
Recently there’s been increased chatter about possible US recession and trouble brewing in the credit markets. I linked below to a typical article out of FT on economists’ assigning a 20% chance of a recession in US. Now I don’t want to dismiss the weak data that is coming out of the US and fully … More On US IG Credit Spreads
Today’s post is about a phenomena observed in many “naturally” occurring data collections that can be exploited in accounting fraud detection. This phenomena is referred to as Benford’s Law and is named after Frank Benford who popularised it. The original discovery is actually credited to Simon Newcomb. The main idea is that leading digits in … More Fraud Detection with Benford’s Law
In today’s post I wanted to describe classification trees. I will concentrate on Classification and Regression Tree (CART) algorithm. As I discuss the main features of this algorithm I will contrast it with other widely used methods to construct classification trees. What A Classification Tree Looks Like: Before diving into the algorithm let’s have a … More Classification Trees
In my previous post I showed a coordinate descent algorithm for solving Lasso coefficients. Lasso model is part of a family of penalized regression models that are popular in machine learning and predictive modeling. In today’s post I want to show you how this model can be used to estimate the monthly average price of … More Lasso model example (LME’s Aluminium Futures Price)
Previously I discussed the benefit of using Ridge regression and showed how to implement it in Excel. In this post I want to present the LASSO model which stands for Least Absolute Shrinkage and Selection Operator. We are again trying to penalize the size of the coefficients just as we did with ridge regression but … More LASSO Regression in VBA
asmquantmacro.com 