Data Science for Business is the book I wasn’t going to read since I’ve already read Machine Learning in Action, Data Mining: Practical Machine Learning Tools and Techniques, and Mining the Social Web. However, I gave in to peer pressure. The pitch for the book is that it is for people who will manage data scientists rather than necessarily be data scientists themselves. The implication here is that you’re paying these data scientists to increase your profits, so you better make sure that’s what they’ll do. You need to be able to understand what data science can and cannot do, ask reasonable questions of data scientists of their models and understand the environment the data scientist needs to thrive.

The book covers several key algorithms: decision trees, support vector machines, logistic regression, k-Nearest Neighbours and term frequency-inverse document frequency (TF-IDF) but not in any great depth of implementation. To my mind it is surprisingly mathematical in places, given the intended audience of managers rather than scientists.

The strengths of the book are in the explanations of the algorithms in visual terms, and in its focus on the expected value framework for evaluating data mining models. Diversity of explanation is always a good thing; read enough different explanations and one will speak directly to you. It also spends more of its time discussing practical applications than other books on data mining. An example on “churn” runs through the book. “Churn” is the loss of customers at the end of a contract, in this case the telecom industry is used as an illustration.

A couple of nuggets I picked up:

• You can think of different machine learning algorithms in terms of the decision boundary they produce and how that looks. Overfitting becomes a decision boundary which is disturbingly intricate. Support vector machines put the decision boundary as far away from the classes they separate as possible;
• You need to make sure that the attributes that you use to build your model will be available at the point of use. That’s to say there is no point in building a model for churn which needs an attribute from a customer which is only available just after they’ve left you. Sounds a bit obvious but I can easily see myself making this mistake;
• The expected value framework for evaluating models. This combines the probability of an event, i.e. the result of a promotion campaign with the value of the outcome. Again churn makes a useful demonstration. If you have the choice between a promotion which is successful with 10 users with an average spend of £10 per year or 1 user with an average spend of £200 then you should obviously go with the latter rather than the former. This reminds me of expectation values in quantum mechanics and in statistical physics.

The title of the book, and the related reading demonstrate that data science, machine learning and data mining are used synonymously. I had a quick look at the popularity of these terms over the last few years. You can see the results in the Google Ngram viewer here. Somewhat to my surprise data science still lags far behind other terms despite the recent buzz, this is perhaps because Google only expose data to 2008.

Which book should you read?

All of them!

If you must buy only one then make it Data Mining, it is encyclopaedic and covers high level business overview, toy implementation and detailed implementation in some depth. If you want to see the code, then get Machine Learning in Action – but be aware that ultimately you are most likely going to be using someone else’s implementation of the core machine learning algorithms. Mining the Social Web is excellent if you want to see the code and are particularly interested in social media. And read Data Science for Business if you are the intended managerial audience or one who will be doing data mining in a commercial environment.

We got five teams:

Co-Ordnance – This project aimed to be a local business tracker. They wanted to make the London Stock Exchange code into meaningful data, but alas, the stock exchange prevents scraping. So they decided to use company data from registers like the LSE and Companies House to extract business information and structure it for small businesses who need to know best place to set up and for local business activists.

The team consisted of 3 hacks (Steve Fossey, Eva Tallaksen from Intrafish and Gareth Morlais from BBC Cymru) and 3 hackers (Carey Hiles, Craig Marvelley and Warren Seymour, all from Box UK).

It’s a good thing they had some serious hackers as they had a serious hack on their hands. Here’s a scraper they did for the London Stock Exchange ticker. And here’s what they were able to get done in just one day!

This was just a locally hosted site but the map did allow users to search for types of businesses by region, see whether they’d been dissolved and by what date.

Open Senedd – This project aimed to be a Welsh version of TheyWorkforYou. A way for people in Wales to find out how assembly members voted in plenary meetings. It tackles the worthy task of making assembly members voting records accessible and transparent.

The team consisted of 2 hacks (Daniel Grosvenor from CLIConline and Hannah Waldram from Guardian Cardiff) and 2 hackers (Nathan Collins and Matt Dove).

They spent the day hacking away and drew up an outline for www.opensenedd.org.uk. We look forward to the birth of their project! Which may or may not look something like this (left). Minus Coke can and laptop hopefully!

They took on a lot for a one day project but devolution will not stop the ScraperWiki digger!

There’s no such thing as a free school meal – This project aimed to extract information on Welsh schools from inspection reports. This involved getting unstructure Estyn reports on all 2698 Welsh schools into ScraperWiki.

The team consisted of 1 hack (Izzy Kaminski) and 2 astronomer hackers (Edward Gomez and Stuart Lowe from LCOGT).

This small team managed to scrape Welsh schools data (which the next team stole!) and had time to make a heat map of schools in Wales. This was done using some sort of astronomical tool. Their longer term aim is to overlay the map with information on child poverty and school meals. A worthy venture and we wish them well.

Ysgoloscope – This project aimed to be a Welsh version of Schooloscope. Its aim was to make accessible and interactive information about schools for parents to explore. It used Edward’s scraper of horrible PDF Estyn inspection reports. These had different rating methodology to Ofsted (devolution is not good for data journalism!).

The team consisted of 6 hacks (Joni Ayn Alexander, Chris Bolton, Bethan James from the Stroke Association, Paul Byers, Geraldine Nichols and Rachel Howells), 1 hacker (Ben Campbell from Media Standards Trust) and 1 troublemaker (Esko Reinikainen).

Maybe it was a case of too many hacks or just trying to narrow down what area of local government to tackle, but the result was a plan. Here is their presentation and I’m sure parents all over Wales are hoping to see Ysgoloscope up and running.

Blasus – This project aimed to map food hygiene rating over Wales. They wanted to correlate this information with deprivation indices. They noticed that the Food Standards Agency site does not work. Not for this purpose which is most useful.

The team consisted of 4 hacks (Joe Goodden from the BBC, Alyson Fielding, Charlie Duff from HRZone and Sophie Paterson from the ATRiuM) and 1 hacker (Dafydd Vaughan from CF Labs).

As you can see below they created something which they presented on the day. They used this scraper and made an interactive map with food hygiene ratings, symbols and local information. Amazing for just a day’s work!

And the winners are… (drum roll please)

• 1st Prize: Blasus
• 2nd Prize: Open Senedd
• 3rd Prize: Co-Ordnance
• Best Scoop: Blasus for finding  a catering college in Merthyr with a Food Hygiene Standard rating of just 2
• Best Scraper: Co-Ordnance

A big shout out

To our judges Glyn Mottershead from Cardiff School of Journalism, Media and Cultural Studies, Gwawr Hughes from Skillset and Sean Clarke from The Guardian.

And our sponsors Skillset, Guardian Platform, Guardian Local and Cardiff School of Journalism, Media and Cultural Studies.

Schools, businesses and eating place of Wales – you’ve been ScraperWikied!

Blasus winning first prize and Best Scoop award (prizes will be delivered, sealed with a handshake from our sponsor).