Experience

Trove Research

Trove Research advocates for the use of the Carbon Market (CM). We provide data and analysis through our subscription intelligence platform, Trove Intelligence. We deal in simplyfying and aggregating numerous data sources, which requires heavy data manipulation, both manual and scripted. Initially brought in as an analyst, I quickly adopted more responsibilities as I had more to offer to the team. Apart from helping various team members, my major projects include:

• Improving the Global Carbon Credit Supply Model (GCCS): quantifying globally available potential carbon stock and forecasting the price of future carbon credits. My goal is to transition the model from R to Python and update data sources. Due to the scale of the analysis, computations previously run on managed univeristy HPC clusters. I was responsible for our transition to the cloud, deciding and building our AWS infrastructure. I proposed a project plan and forecasted costs to our COO. We’re currently building an R Shiny application to best display our results.

• Project Issuances profiles: quantifying how different project types have issued their credits during their crediting period, by looking at historical issuances of over 4000 different projects, collected from 4 different registries. These results were then fed into our Carbon Credit Supply Model for forecasting

• Carbon Credit Demand: forecasting the demand of carbon credits for over 400 companies, producing ETL scripts that feed data into our Trove Intelligence Platform (PowerBI). Working with two other analysts in both R and Python

• Teaching team members about Data Science: as most of Trove’s data manipulation and analysis occurs in Excel, I helped transition the team to modern data science methods, such as python environment management and version control using git & GitHub