Ashley Wright

Research Fellow

Monash University

Biography

Driven to deliver innovative, data based, solutions which provide impact and value. Not one to shy away from a challenge, I completed a PhD in 2017 which focused on improving forecasting skill at Monash University.

Career highlights for me have involved engaging with clients and working in cross functional teams to deliver strategic analytic solutions for Australian banks.

Outside of work you can find me training in Brazilian Jiu Jitsu (BJJ). It is a martial art that is often described as human chess. I enjoy the challenges, exercise, and culture associated with BJJ.

View my CV

Interests

All things machine learning
Communicating data driven insights
Extracting value from data

Education

PhD in Optimisation and Modeling, 2017

Monash University
BEng in Civil Engineering, 2012

Monash University
BSc majoring in Applied Maths & Physics, 2010

Monash University

Posts

Neural Network Driven Insights into Electricity Consumption Data During COVID-19

The ongoing COVID-19 pandemic has caused widespread disruptions to everyday life and the global economy. Many existing forecast models no longer provide the same accuracy they once did. Consequently, being able to account for the change in conditions would prove quite valuable.

Oct 18, 2020 4 min read

Neural Network Driven Insights into Electricity Consumption Data During COVID-19

Attributing Forecast Errors to COVID-19 Restrictions

There are a number of situations in which past data of the observation we are making forecasts for is not available. Possible reasons include time lags between data collection and data availability, and the time taken to quality control data.

Last updated on Oct 18, 2020 5 min read

Attributing Forecast Errors to COVID-19 Restrictions

Accounting for Model Drift

To improve forecasting capability during uncertain times it is necessary to both understand and address model drift. The hypothesis I aim to test is that electricity consumption forecasts will be more prone to errors in states that have seen more severe and prolonged restrictions as a result of COVID-19.

Last updated on Oct 18, 2020 4 min read

Developing Neural Networks to Forecast Electricity Consumption

Using the daily Victorian electricity consumption as an example, this blog will outline procedures to develop a forecasting model. To enable scheduling of energy supply for the next day I develop one day ahead forecasts.

Last updated on Oct 18, 2020 4 min read

Developing Neural Networks to Forecast Electricity Consumption

Exploring Electricity Consumption Data

The COVID-19 pandemic has changed our understanding of uncertainty and what exactly normal is. We have seen economies free fall, toilet paper being hoarded, and unprecedented amounts of data made publicly available.

Last updated on Oct 18, 2020 4 min read

Projects

improving Flood Forecast Skill Using Remote Sensing Data

Accurate flood predictions are critically important for limiting the damage caused by floods. This research integrates remote sening data into flood forecasting models.