No images? Click here
Data Analytics Newsletter #15
February 2020
,
The Data Analytics Practice Committee (DAPC), the Young Data Analytics Working Group (YDAWG) and the Actuaries Institute are pleased to bring the latest in the world of Data Analytics to your inbox, and to share some of our recent work with you.
In this edition, we focus on data journalism - data analytics and its role in helping evaluate and understand current events around the world. We hope you find the topics interesting, and there are lessons from these data visualisations and models that are relevant to all actuaries working with data analytics.
Contents
1. Coronavirus outbreak - five questions to ask big data
2. Actuarial Hackathon 2020
3. US Elections: Democratic Party Primaries
4. Reproducibility in analytics
Coronavirus outbreak - five questions to ask big data
The COVID-19 coronavirus has spread across major population centres in China, despite unprecedented containment measures in 14 cities, as well as internationally. The number of infections and deaths have now surpassed the 2003 SARS epidemic. There is concern for a severe impact to global health, with potential flow on effects to supply chains and the global economy.
YDAWG member Zeming Yu writes from Beijing with a review of data on the outbreak up to mid-February.
For further information, Actuaries Digital also has coverage on the outbreak.
Actuarial Hackathon 2020
Expressions of interests are open for the Actuarial Hackathon 2020!
The Hackathon provides an opportunity for actuaries to channel their expertise of numbers and business into making a difference in society. You will be part of a small team working alongside a non-profit organisation to address their needs through analytics.
US Election: Democratic Party Primaries
The run up to the United States' presidential election has begun and the Democratic Party are currently holding their primaries. Candidates campaign, fundraise, gain and lose popularity in debates, and some will drop out as staged regional votes take place to select the next Democratic representative who will challenge President Trump.
In a recent feature, political and statistical forecasting site FiveThirtyEight explains its forecasting model for the outcome for this complex political process that has limited data, non-stationary or non-linear effects, and unusual exception with some caucuses having different voting rules. This is not a problem that can be easily solved by cleaning data and applying a GBM!
Reproducibility in analytics
Often in actuarial analysis regular reports on data are produced manually through Excel and Word, and can be prone to issues of reproducibility. This presentation to the Institute and Faculty of Actuaries describes how data science pipelines can introduce better rigour, version control and quality assurance.
The case study of the BBC visual and data journalism team and the journey of how they have used R to produce consistent, professional-looking, and reproducible visualisations should be of interest to any actuary that is looking to improve the quality of their reporting.
Disclaimer: The Institute wishes it to be understood that any opinions put forward in this publication are not necessarily those of the Institute.
 |  |  |  |  |
Level 2, 50 Carrington Street
Sydney NSW 2000, Australia
t +61 (0) 2 9239 6100
f +61 (0) 2 9239 6170