AI opinion on population trend

[abezverkhiy]

Correct, if you are coming from the point of the exact science.

Think differently and do not turn it into an academic discussion.

You have a chart that moves up and down. You plot events on this chart. Next, you ask yourself - what similar properties of those that moved it up and moved it down. And focus on making only those events that moved the chart up not down. Simple.

One can say there is a magnitude of the events in and out of the game. Of course. But there are significant ones - ROR patches and less insignificant - gossips of new server, public holiday in a country X, earthquake in a country Y etc. Focus on the most important ones or you get a 'paralysis by analysis' situation.

[rorswar]

1) the data “analysis” is useless and doesn’t tell us anything
2) we know population has been trending downwards over time, anecdotally we have all experienced that
3) you don’t need a half baked data analysis to know rhat

[abezverkhiy]

it will not tell you anything Mr Troll who only comes here to raise your self esteem by pissing everyone over.

[rorswar]

it will not tell you anything Mr Troll who only comes here to raise your self esteem by pissing everyone over.

So, enlighten me, professor.

On a statistically significant basis, what does this “analysis” tells us when you state that you need to “… Focus on the most important ones”, and you leave exactly the most important one - seasonality - out.

Also, what was the point of this analysis? To showcase a downward trend? Everyone who plays the game knows that. Root causes of that decline? I haven’t seen any conclusive ones, other than potential correlation.

And anyone with a 101 understanding of analysis knows that correlation is not causation. As it stands, you spent as much time on this analysis as you spent 30s in stealth.

So a more mature response would be:

“Hey, I had some fun what ChatGPT and player numbers. There appears to be a long term decline in player base, but I can’t tell for sure as the data doesn’t go back far enough, and thus I also haven’t been able to include seasonality.

There seems to be some correlation between some events and sudden moves in the playerbase, but it’s difficult to ascertain as there are too many internal and external factors that impact the analysis.

It’s been fun anyways.”

At the moment the “fun is decreasing” thread which is filled with hormones and emotions providers a more solid scientific basis.

[abezverkhiy]

Everything was explained above Mr Troll. You either did not read or looked for a wrong thing. Anyway, the post is not for you, move on!

[rorswar]

Everything was explained above Mr Troll. You either did not read or looked for a wrong thing. Anyway, the post is not for you, move on!

I did read, Mr Professor. And that appears to be the problem, as if someone challenges you on your analysis, you retort to insults.

I still haven’t see any comments on why your “analysis” is useful and uses proper statistical approaches, as if it does not, then the “insights” are just based on emotions and we all know how biased you are after WH nerfs, given your two weeks post history of “it’s the end of the world for stealth classes.”

It is no coincidence that this thread materialised a few days after the patch landed, and thus the purpose of this thread is in bad faith, as you aim to use a downward population thread to once again showcase how badly your beloved WH got nerfed.

You then try to use “statistical evidence” to underpin your argument.

And that’s why I object. As this thread is steeped in emotions and bad faith, rather than what you portray it to be.

It also undermines the devs. Fun may have decreased for you, but then provide meaningful insights and recommendations rather than hiding behind ChatGPT using a very limited data set.

Anyway, the “analysis” tells us nothing, move on!

[abezverkhiy]

Bye Mr Troll, hope you have a nice day! The thread is not intended for you and wasting time on you is not on my list.

[sharpblader]

Sorry king but you're wrong on this one.

I admire how you play your way uncaring of what others think, but based on the industry practice of analysing a liveops game service, rorswar is correct here.

You have to account for seasonality.

Very simply put, imagine its the Christmas holidays. Number of players has increased. Probably because more people have time on their hands to play. Once the holidays are over, users plummet. Was it the game's fault or people just don't have as much time anymore?

To measure if the game did better, we compare what happened this Christmas and the Christmas before. This is an oversimplification but I hope you get the idea.

If the game did worse this Christmas compared to the one before, there does seem to be a game related problem.

Now the analyst brings out retention models to locate where the game is bleeding players. Generally in old live service games like RoR, the problem is usually found in deteriorating inflow of new users.In other words, New User Retention has decreased and is at a number which is not enough to maintain the same player base (Outflow > Inflow). Ok, new player problem identified, maybe it's time to improve FTUE and onboarding.

Now, how are the regular or recurring players doing? Lower than last period? Probably time to introduce new content/balance changes to shake things up.

My explanation is an oversimplification, there's much more to it and can be statistically significant only with all the data available. The current chart you have I believe is CCU which is indicative at best.

Anyway, even after all this work, the analysis is the easier part. Executing solutions is a completely different topic.

[rorswar]

Anyway, even after all this work, the analysis is the easier part. Executing solutions is a completely different topic.

Exactly. And that’s the point, as the “analysis” can’t help pinpoint reliable root causes given the limited data set, and thus it serves no purpose other than underpinning a personal and emotional argument. It does not help the game. It does not help the devs.

[Bankei]

Anyway, even after all this work, the analysis is the easier part. Executing solutions is a completely different topic.

Exactly. And that’s the point, as the “analysis” can’t help pinpoint reliable root causes given the limited data set, and thus it serves no purpose other than underpinning a personal and emotional argument. It does not help the game. It does not help the devs.

I put Guild Wars 2 steam data into super neutral Claude and told it to "tell me interesting things, no no, MORE interesting"

Then I put BDO data into the ultra mega neutral Gemini and told it to "make the bestest most smartest analysis of the numbers because i'm the goodest analyst with 21+ years of looking at ... numbers?"

Both the models told me MMOs are in decline and that I didn't need an analysis for that... weird

Somehow, even that is more useful than the Professor lecturing us on this thread