Julia Back Email & Phone Number

Melbourne, Victoria, Australia

• Analysed large, complex datasets of real plant data including 28 features for Shell to identify significant correlations, developed predictive equations for process optimisation using Python and R, resulting in time and budget savings.• Developed a prototype for predicting gold prices using 20 years of data for a client, providing visualisations and reports for decision-making using Power BI.• Conducted time series analysis for Proxy Resources New Caledonia to predict nickel prices and performed statistical modelling to identify trends using Python and R, creating visualisations with Power BI.• Collaborated with stakeholders from overseas to ensure alignment on project expectations and progress, delivering timely insights and recommendations.

Melbourne, Victoria, Australia

• Analysed population-based data to assess the impact of water-related services and infrastructure on urban hear and air temperature, utilising PSP files, GeoJSON data and QGIS.• Built predictive WSC scenario models to analyse variables affecting urban heat and to inform decision-making and policy development.• Assess the models to quantify the risks, costs and benefits by changing input data up to 10 variables such as density of house and population, the number of industrial areas, trees, buildings, types of roads, etc.• Reported findings to stakeholders, documenting data management processes and suggesting highly sustainable solutions.

Melbourne, Victoria, Australia

• Build Augmented Reality visualisation for engineer in the Museum of London collaborating with Amazon Web Services (AWS) and RMIT Cyber Ready CIC• The aim was to solve the Museum of London’s business problems, maintenance engineer’s safety concerns, organising planned maintenance and reactive maintenance tasks and unreliable work quality from engineers• For consistent preventive maintenance work quality from engineers, AR tutorial video was developed by AWS Sumerian and shows engineers how to fix the machine. This is because engineers relied on over 1000 pages of original documentation. This contained asset’s location, procedural steps, scheduled date and equipment. Therefore, this AR tutorial engaged engineers to understand tasks easily, notice what tools are necessary and enhance their safety.• To reduce downtime for engineers, optimised route is provided using AWS Sumerian• Since the most urgent task was from the reactive maintenance, the Museum of London needed to plan unplanned tasks. Our intelligent application can predict the reactive maintenance task through engineer’s reported data and provide to the manager for recommendation. This can save unexpected energy/water consumption and asset downtime

Master'S Degree, Data Science, High Destinction

Bachelor'S Degree, Software Science