I am delighted to have now completed the Microsoft Professional Program for Data Science. It has been 10 online courses (taking a total of 322 hours) over just more than 11 months and my average (mean) mark over the 10 courses was 96.6%. The final course was a capstone project which involved analysing data from the 2015 earthquake in Nepal, building a model to help predict the degree of damage to buildings (amongst other things to help emergency response teams prioritise rescue efforts) and producing a report on this. This was an extremely practical way to complete the course.
I have created a series of slides (collected together in a Microsoft Sway online document) showing the main stages of my journey. You can see them at https://sway.com/lsUjwGITuGFpsHIM?ref=Link
(This is a follow up to part 1 which you can see here. Posted by Patrick Lee on 15 August 2017 at a different location, but migrated here on 05 Feb 2018).
Proposed First Draft
I’ve now completed a first draft of a proposed standard, as a Microsoft Excel file (118kB, so quite small). You can download it here. Comments/criticisms most welcome. Let’s make this happen!
Why Microsoft Excel?
I’ve chosen to put it in an Excel file (as opposed to CSV or other non proprietary formats) for the moment because Excel offers the following advantages:
- we can put several different worksheets/tables in a single file
- field headings can have explanatory comments
- I’ve using colour coding to visually group similar fields.
(Posted by Patrick Lee on 14 August 2017 at a different location, but migrated here on 05 Feb 2018).
I’ve just watched several videos and read a good article on the Semantic Web (also called Linked Data and Web 3.0, in which not just humans but computers can understand content) by Brian Sletten. It would be good for the pensions and insurance industry to play its part in helping the web move towards 3.0 (something that will have even more of an impact than Web 1.0 did in about 1998, and Web 2.0 – the advent of social media which enabled everyone to connect and become a publisher – in about 2008) and I will be writing more about this soon.
(Posted by Patrick Lee on 10 August 2017 at a different location, but migrated here on 05 Feb 2018).
You may not know that Excel 2016 added some useful new charts for analysing data. I particularly like the Treemap, Box & Whisker and Pareto charts. (The images below are taken from this Microsoft post, please see that link for more detail on these and other charts).
(Posted by Patrick Lee on 8 August 2017 at a different location, but migrated here on 05 Feb 2018).
I have long thought it would be useful for there to be a standard format for exchange of data files for DB (Defined Benefit, i.e. final salary or career average revalued) pension plans, at least in the UK initially.
This would make it easier for pension plans to share information (with actuarial consultants, but also other advisers e.g. buyout companies, investment analysts), not just in mergers and acquisitions, but also in risk transfers (longevity, or pensions buyouts) and would improve the comparability of analysis across companies by investors etc. It should also reduce costs for trustees and plan sponsors, and may increase the quality of the data held.