Analysis Paralysis

At some point this year, I let my laptop run flat-out for almost two weeks just to answer one question: how much of a four-player board game is “skill” and how much is “luck”? That sounds excessive, but there was a catch: before I could even start those simulations, I had to fix a basic problem. Elo – the rating system we’ve been happily using so far – only really knows how to handle one-on-one duels.

Whether a game counts as “skill” or “chance” isn’t just a pub argument — in many countries it’s a legal distinction. Roulette and blackjack live on the “chance” side; tennis and chess are filed under “skill”. Different rules, different taxes, different ways for people to lose money.

The trouble is that this line is usually drawn by tradition and gut feeling. Is poker really “more skill” than backgammon? Is snooker closer to roulette or closer to chess? A group of economists tried to answer that question more systematically: instead of arguing, measure how “skill-heavy” a game is in practice by looking at the Elo ratings of all its players. We’ll meet their work properly in a bit.

The cat’s out of the bag and the winners have been announced 🗄️!

After two year of complaining how the ceremonies went on for too long, it appears the jury finally listened to me and made it snappier, while still retaining the sections highlighting all the various facets of the hobby. Kudos! I don’t know if the presenters gained more experience in hosting the show, or if their non-polished charm is simply growing on me, but I definitely found the whole thing more enjoyable. (Don’t forget the Empfehlungsliste really had me cracking up…)

The waiting is finally coming to an end! On Sunday, July 13, the jury will announce the winners of Spiel des Jahres and Kennerspiel des Jahres 2025. As always, there’s six games hoping to win one of the two most important awards in gaming – and one hopeless geek trying to predict which will be the lucky ones. 🤓

Nominations are out 🗄️! The jury selected a total of sixteen games for their longlist, nine for Spiel des Jahres and seven for Kennerspiel des Jahres. Out of these games, three games each are nominated for the two awards and can hope to get the coveted meeple added to their covers on July 13.

Spiel des Jahres 2025 is around the corner! As with the previous five years, I’ll try to predict what games have the best shot at ending up on the longlist (aka recommendations) and the shortlist (aka nominations) when the jury announces their picks on May 20th.

As every year, I’ll let the algorithms speak, and I’ve doubled down on the path I’ve started last year when I put more focus on jury members’ reviews. Back then, I simply averaged all available reviews to obtain a proxy for the “jury review”. The major problem with this are of course the gaps in the data for missing reviews. Luckily, we have a method to fill those gaps in the form of our recommendation algorithm. So this year, I’ve put 50% of the weight on the individual recommendations for the 14 jury members and 50% on the “recommendendations to the jury”. This way, I was able to calculated a score for all eligible¹ games. Our very own Kennerspiel score is then used to sort those into their respective list of the top 10 contenders for either award. As always, you can find the complete code on GitLab and the complete results here.

Welcome to the Crucible

This blog is usually all about board games, but let’s stretch the definition just a little: snooker is, after all, one of the most widely followed tabletop games in the world. And with the World Championship kicking off at the Crucible Theatre in Sheffield, I couldn’t resist the excuse to dive into something a bit different.

In the last article, we looked at how Elo ratings can be used to measure player strength over time. This time, we’ll take it a step further: using historical match data, a bit of Python, and a lot of simulated tournaments, we’ll try to predict who’s most likely to lift the trophy this year. We’ll also compare our predictions to what the betting markets say – and see whether the wisdom of the crowd agrees with the cold logic of the model.

Chance in games is like seasoning in food — it’s all about the right amount. Just imagine a life without chance, where everything could be planned out strategically. That would get boring over time. In a game, I want to have experiences — I want adventure. A good game is like a miniature life, one where I can make mistakes, enjoy a streak of bad or good luck, and still recover. But you shouldn’t be at the mercy of randomness. There should be ways to compensate — like a friend of mine in CATAN, who always complains about his bad luck, prompting others to treat him more kindly and rarely target him with the robber. In the end, he often wins — to everyone’s surprise.
— Klaus Teuber on the importance of randomness in games in CATAN-News 1/2000 🗄️

[Read More]

This subject has nothing to do with games nor data science, but chances are that amongst the readers of this blogs are many who appreciate mathematics – and its beauty. Long before Recommend.Games, I’ve had a blog on the Riemann Hypothesis – the famous conjecture which is usually formulated in terms of the zeros of the complex Riemann \(\zeta\)-function, but is really about the distribution of prime numbers. If you’re curious to learn more, check out the blog. 🤓

Bias is a bit of an ugly word, isn’t it? It certainly has become one of those battle phrases in the culture war, where both sides of the argument accuse the other of forcing their biases onto society. Board game reviews frequently need to justify themselves for their biases affecting their views. Dan Thurot 🗄️ recently wrote a very eloquent piece on the matter, diving deeper into different kinds of biases.

But bias also has a well defined meaning in statistics. Moving from emotions to cold hard numbers, the word bias loses its antagonistic nature and simply becomes a measurement one might want to minimise or remove entirely. Hence, debiasing the BoardGameGeek (BGG) ranking is about asking the question what it would look like if we removed the influence of a particular parameter. One such parameter is a game’s age: we’ve seen in the previous article that ratings have gone up over time, so removing the age bias from the BGG ranking means correcting for this trend.