Jupyter notebook here Given a fixed amount of avliable resources, optimise allocation to maximise returns across a set of products with variable returns. Following the Modern Portfolio Theory m...
A deep dive on GLM's in frequency severity models
Jupyter notebook here This notebook is a deep dive into General Linear Models (GLM’s) with a focus on the GLM’s used in insurance risk modeling and pricing (Yan, J. 2010).I have used GLM’s befor...
A guide to clustering large datasets with mixed data-types
Please see the updated version of this post here
How to containerize a simple Rest API using Python Flask
You’ve conducted your research, analysed the data, built models, and packaged everything up in a user friendly application that is ready to be shared and published within your research community an...
Using machine learning to cleanse datasets: classifying column headers in data tables
When dealing with large volumes of inbound data files and from multiple different sources, the data recieved can often come in a variety of formats, structures and to varying standards. One partic...
An introduction to hashing functions for data mining
This post is intended to provide a quick introduction to hash functions and to discuss some practical applications of hashes in data mining and machine learning. The aim of this post is to provide ...
Hello Jekyll!
Hello and welcome to my new Research and DataScience portfolio page. Update March 2021 I have now adopted the Chirpy theme. On this site I’ll be posting links to projects, demo’s and training mat...
Earth Surface Processes and Landforms: classficiation of rare events for landslide early warning systems
Link to my 2018 paper in ESPL. Abstract Translational landslides and debris flows are often initiated during intense or prolonged rainfall. Empirical thresholds aim to classify the rain conditio...
Environmental Research Letters: agent simulation of natural hazards in complex networks
Link to my 2017 paper in ERL. Abstract Disruptions to transportation networks by natural hazard events cause direct losses (e.g. by physical damage) and indirect socio-economic losses via travel...