Practical data science projects often include an aspect of anonymisation to carefully remove sensitive information prior to analysis; here we demonstrate several complimentary techniques and principles.
Technology moves incredibly quickly these days and practical learnings only slowly formalised into academic courses; fortunately there's many semi-professional and purely social ways to keep up.
In this technical article we explain why and how to use Singular Value Decomposition (SVD) for feature reduction: making large datasets more compact whilst preserving information.
Data science doesn't just lead to insights and products: here we define SPEACS, a generalised analytical process that highlights the many business benefits at every stage.
Real data is often unavailable for creating demos, learning and especially for publishing. Here we describe methods to generate realistic artificial data which has fewer constraints.
In the final article of this technical series we generate outputs to estimate the value of mortality swaps and discuss the concept of pricing tail risk.
In the second article of this technical series we put the pieces together to begin estimating the value of a mortality swap, an esoteric insurance derivative.
This series discusses a novel approach to modelling mortality swaps: an esoteric derivative insuring against the risk of life-contingent assets like annuities and life insurance policies.
As a highly mobile consulting company we need to 'take the office with us' when on the road; happily there's several fantastic tools for the job.
Converting postal addresses into geospatial lat/lon coordinates - aka geocoding - is cheaper and more accessible than you might imagine, and enables powerful statistical analyses.
We're recently back from R in Insurance in Amsterdam where we heard several interesting talks, delivered one of our own, and met some really great people.
Visualising data is important for aiding intuition & good understanding, but high-dimensional datasets can be hard to display. Here we demonstrate techniques to tackle the issue.
Like any collaborative business effort involving research & development, a data science function should be built carefully in order to enable the best expertise and technologies.
In the final article of this series we investigate the behaviours of different distribution distance metrics to let us automatically determine the scale of the change.
In the second article of this series we continue our technical discussion on using Bayesian analysis to probabilistically estimate the effect of a business process change.
In this series of articles we'll discuss the use of probabilistic modelling to help efficiently evaluate changes to business processes and the success of marketing campaigns.