The Second Ashes Cricket Test 2019

The Second Cricket Ashes Test has concluded as a draw (link).

During the test match, Australia had to respond to two England scores of 258 in each innings.

My estimate was that England was required to take a wicket every 26 runs in each innings to win the game and level the test series. My record:

First Innings (Rate 26 Runs per wicket)

Australia were bowled out for 250 runs.

Second Innings (Rate 26 Runs per wicket)

The game ended with an Australian score of 154 for 6 wickets (link).

A Comparison of Both Innings

(Using the gridExtra package)

Decision Intelligence and Data

Cassie Kozyrkov (link) has written about “decision intelligence is a new academic discipline concerned with all aspects of selecting between options”.

This decision intelligence “brings together the best of applied data science, social science, and managerial science into a unified field that helps people use data to improve their lives, their businesses, and the world around them”. Cassie views it as a “vital science for the AI era” and it turns “information into better actions at any scale”.

Cassie lists some basic terminology of the discipline:

Decisions: It’s through our decisions — our actions — that we affect the world around us. (It is “any selection between options by any entity’.)

Decision Maker: The person who is responsible for decision architecture and context framing, a creator of meticulously-phrased objectives.

Decision Making: taking responsibility for an action when there were alternative options.

Taxonomy: decision sciences (qualitative side). Cassie suggests “Think of the decision science side as dealing with decision setup and information processing in its fuzzier storage form (the human brain) rather than the kind that’s neatly written down in semi-permanent storage (on paper or electronically) which we call data“.

She adds: “Strategies based on pure mathematical rationality without a qualitative understanding of decision-making and human behavior are relatively naïve and tend to underperform relative to those based on joint mastery of the quantitative and qualitative sides”.

A large part of Cassie’s article looks at decision making and facts. She observes “with training in the decision sciences, you learn to reduce the effort that it takes to make rigorous fact-based decisions, which means that the same amount of work now gets you higher-quality decision-making across the board”. But, alas, “we live in the real world and often we must work for our information”.

She adds “Data science gets interesting when you’re forced to make leaps beyond the data…”. This involves the bringing together of diverse perspectives in decision intelligence.

It requires us, as Splunk suggests in a Priceonomics post (link) to make some important clarifications about dark data (“most of the data collected by businesses simply goes unused”) and our role in making decisions about the data we have collected and see as important.

Photo Credit

Frederick Tubiermont on Unsplash

Sylwia Bartyzel on Unsplash

Data Scientists in the NFL: An Example

A few weeks ago, I wrote about an example of data science in basketball (link).

This week, the Philadelphia Eagles (link) have provided an example from the NFL. They have advertised three posts:

Director of Analytics – Football Operations (link)

Senior Quantitative Analyst – Football Operations (link)

Quantitative Analyst – Football Operations (link)

The Director of Analytics will “work closely with the VP of Football Operations and Strategy to shape analytics within Football Operations”. The position description includes the following:

The Director of Analytics will use data to address key issues in the modern NFL front office including player evaluation, game preparation, resource allocation, sports science, and player development. A strong candidate will have significant work experience, an advanced degree in a quantitative discipline, and a demonstrated ability to interact with a diverse set of stakeholders. We will prioritize applicants with deep knowledge of modern statistical techniques and the creativity to identify novel analytical directions. The position requires strong organization, communication, and leadership skills, and the ability to work on widely varying projects with distinct audiences.

Candidates for the position “must have the ability and statistical range to draw insights from many different forms of football data and a passion for improving football decision-making”.

The qualifications expected of candidates for the Director’s role are:

  • Outstanding analytical and quantitative skills
  • 3 – 5 years of significant work experience
  • Advanced degree with strong performance in statistics, machine learning, or econometrics
  • Excellent at data management and statistical analysis
  • Experience with multiple statistical software packages and/or programming languages
  • Strong communication skills, both verbally and in writing
  • Vision to plan for and adapt to changes in available football data
  • Football knowledge to identify key questions and topics for analysis

The Senior Analyst “will have relevant work experience and/or graduate-level training in a quantitative discipline”. Applicants for the post “should have a deep understanding of modern statistical techniques, with proven ability to execute on their ideas”. Candidates will be expected “to be well-versed in sports analytics research and methods”. The qualifications listed for the position:

  • Outstanding analytical and quantitative skills
  • 2-3 years of relevant work experience or comparable academic experience
  • Advanced degree in statistics, machine learning, or econometrics
  • Highly skilled in statistical software for data management and analysis
  • Software development and data visualization skills are a plus
  • Ability to communicate complex ideas to diverse audiences
  • Passion for football

The Analyst “will be able to work with football data to draw insights and improve decision-making”. Applicants should have “the quantitative skills to analyze complex problems and the technical ability to implement their ideas effectively”. Candidates will be expected applicants to have a solid foundation in statistical modeling.  The qualifications listed for the position:

  • Undergraduate or graduate degree in a relevant field
  • Strong analytical and quantitative skills
  • Experience in statistics, machine learning, or econometrics 
  • Proficient with data management and analysis in statistical software (e.g. R, STATA)
  • Software development and data visualization skills are a plus
  • Good communication skills
  • Ability to work independently with a hands-on approach.
  • Passion for football 

Photo Credit

What’s understood doesn’t need to be explained (Twitter)