# When should Machine Learning be used? By Torran Elson

In contrast to statistics which places greater emphasis on inference – finding the model that best explains the data – machine learning emphases a model’s predictive ability. With this in mind, we can form a list of problems that are suitable to a machine learning approach...

# Improving seasonal forecasts to make sure we all get fed By Christopher Nankervis

Our world’s population is projected to grow. This has sparked international food strategies to support new crop technologies that improve crop output efficiency. Yet limited land available for farming in the UK has been compounded by evolving land use. Weather Logistics, aims to tackle food production issues through better management of UK agricultural risks, by producing fine scale predictions on 25km space-scales at challenging 1-6 month ‘seasonal’ timescales...

# How Many Fish in the Lake (or Sweets in the Bag)? By Dr Robert Leese

Hannah and her sweets have been a hot topic of discussion over the last few days, since the following question appeared on a GCSE mathematics paper, sat by 500,000 teenagers last Thursday: "There are n sweets in a bag. Six of the sweets are orange. The rest of the sweets are yellow. Hannah takes at random a sweet from the bag. She eats the sweet. Hannah then takes at random another sweet from the bag. She eats the sweet. The probability that Hannah eats two orange sweets is 13. Show that n2-n-90=0." Why were the sweets so sticky?

# Playing by the rules: getting auctions right By Dr Robert Leese

Since 2007, together with colleagues at the Smith Institute, I have spent a good deal of time working with clients around the globe on auctions for radio spectrum licences. Bearing in mind that auction outcomes can shape a country's mobile telecommunications industry for a decade or more, the tasks of getting the auction designs right […]

# Data Science, think Mathematical Science By Dr David Allwright, Dr Robert Leese and Dr Zoe Kelson

Are the mathematical sciences fundamental in data science? Yes! Well, we think so anyway, and a newly formed and quickly growing data science community agrees. From mathematical thinking to complex analytics to method validation, maths in all its stages can add value and create impact.

The purpose of collecting data is to learn from it; and we learn by asking questions. In the data world questions come in the form of estimators that construct some properties of the data. So what are the right questions to ask?

# Festive Fun By Dr David Allwright, Dr Zoe Kelson and Dr Heather Tewkesbury

The mathematician goes out to measure the area of a flat triangular field ABC using an electronic device his sister has just given him, on which you can push a button, walk round an area, push the button again and it tells you the area your path has enclosed. When he arrives at A, he decides he can't face walking round the whole field but there is a prominent tree X on the opposite side (BC)...

# Why are Secure Passwords Difficult to Remember? By Dr Owen Jones

Making up passwords is annoying. And when you finally come up with something, you always get a message saying it needs to have a capital letter in it, or a number, or a special character. In this post I’m going to explain the maths behind those bothersome messages and suggest a better way to choose […]

# Particle Swarm Optimisation: A Case of Mistaken Identity? By Dr Owen Jones

Recently I was working on a project which needed an optimisation algorithm. In other words, we had a function $f(x)$, where $x$ is a vector, and I needed to write a computer program to try and find a value of $x$ which made $f(x)$ as small as possible. Since we wanted the flexibility to change $f$ later, so we were limited to a black box optimisation algorithm, i.e. one that doesn't use any special features of the function $f$, including the derivatives of $f$...