What is qPTR? I was told that this will increase that metric but I cannot find a any clear messaging on what this metric is.
That link is private. (This message is not long enough to post without this extra filler.)
try the link in the original comment now, it should be working.
My guess is top one, correct me if I’m wrong
My experience has 10 thumbnails and yet when I click edit active thumbnails, I can only choose from seven of them, with the last three not being shown at all. I assume this is unintentional.
Currently you can set 2-5 thumbnails to active for personalization. But you should be able to see all the thumbnails you uploaded - check to see if there’s pagination.
I don’t see any way to flip pages. I uploaded the three new thumbnails after using this update for the first time and setting some thumbnails to be used, so maybe that somehow caused an issue where the edit active thumbnails page isn’t recognizing the new thumbnails.
This is a great idea! For my games where I am uploading only one thumbnail, however, it is never appearing on the game page. It shows up in the developer hub as the selected thumbnail, but never on the actual page. I believe the image is already being moderated too. I have yet to upload multiple thumbnails.
EDIT: I have made a simple mistake, the thumbnails are now separated by home and experience page. This is also a good idea, I was just confused. Apologies!
I’m laughing you used my quote next to those eloquently worded reviews praising this feature. This is seriously great though. Beyond anything I requested in the past. Would love to see stuff like this perhaps expand to Titles and Descriptions one day.
Great tips and very useful to all roblox creators
Sorry for bumping up this post. I have played this feature multiple times and I wonder how the ‘qualified play’ is counted. Does it include existing players or only new players who have not tried my game? In my iterations, I used the old winning thumbnail as the baseline to compare the performance of the new thumbnails. However, the old winning thumbnail always wins. I’m not sure if this is because my new thumbnails are not effective or if existing players click and play the game because they recognize the old thumbnail from when they first saw it.
Amazing update. I have some more suggestions:
- Can we also have an option to personalise the landing page thumbnail? I think players won’t see the winning thumbnail when they land right? If users currently only see the thumb we manually upload for the home page, they might be presented with a homepage thumb that isn’t as relevant to them. This way we might be able to squeeze more % from Page Landing → Play portion of the overall QPTR
- Will there be any plans for optimising against against revenue or LTV?
- If we could choose different optimisation / personalisation models that would also be great. For example when starting out I may prefer to optimise against QPTR but over time I might want to dial it more towards Revenue.
- Maybe a more elegant approach that wouldn’t require any configuration would be where the thumbnails are optimised towards the same mix of metrics the algorithm looks for.
- Icon personalisation would be great. In some spots they drive new users (inside other game page recommendations) and on others they drive repeat play by existing users so someway to personalise these on not only the home page but also on a per experience page basis (the experience where the recommendation is occuring) would be great.
Thanks Tonkness. Good feedback:
- Yes making landing page thumbnail match the personalized thumbnail would be ideal. Will look into effort required.
- Revenue and LTV are too down-funnel for the algo to make real-time decisions on which thumbnail to surface. Might be a way to do it, will think about it.
@here Hey folks, happy new year.
We’re excited to see record breaking adoption for thumbnail personalization and now that you’ve all had time to play with it - what further improvements can we make?
Let us know in the replies Thanks.
Can the spreadsheet/table be condensed please?
the thumbnail personalizing is cool and all but it’s been 9 days since the new year
A few more ideas:
Adding / removing thumbs
- Would be nice if there was a way to add / remove thumbs without having to restart with all the thumbs once again. The issue now is restarting gives new thumbs equal allocation of impressions for a period (seems 12-24 hours).
- I’ve found myself wanting to test more thumbs, but hesitant in case any new thumbs performance is significantly worse and could end up messing the games performance with the main ranking algo. Currently I have two great performing thumbs, but if I add 3 new ones to test and they turn out to be duds, it’s going to really impact my overall performance, because for a period they’d be receiving equal allocation as the existing proven thumbs.
- What would be useful is if I could add more thumbs and be able to choose the % allocation of impressions they get (I’d probably give them 5-10% so they don’t pull too much traffic away from the top performing ones). Once the algo is getting enough data to decide how it should rank, it can then decide its own impression allocation. Or a simpler approach could be the algo just providing a minimum number of impressions it needs to start making allocation decisions and then slowly increase / decrease as needed once enough data starts coming in.
Optimizing towards Revenue / LTV / custom actions
- Revenue is pretty down funnel and there might not be enough data gathered to do quick ranking decisions, but it would still be nice to optimise towards other more up-funnel LTV proxies such as QPTR of premium users, QPTR of high GDP countries etc. For example, I may have two thumbs - the first has a higher overall QPTR but a second thumb may have a lower overall QPTR but for USA it’s higher. In this case I would probably want to algo to pick the USA thumb with the lower overall QPTR instead.
- Choose to optimise towards other metrics - retention, engagement time etc
- Optimise towards a custom event inside the game. I know that certain behaviours from users within my experience will give me certain results. For example, users that reach level X, play for X minutes etc might be more likely to spend in the game. Or users who meet certain events may just perform in a particular way I want (may be more likely to retain for example).
Another piece of feedback:
Returning vs New personalization.
- Over time, the proportion of home recommendation traffic coming from returning users tends to increase. Often what motivates existing users to return is quite different to what motivates a new user.
- Currently I use icons with imagery showing new content which generally informs existing users to return back, but those icons wouldn’t be suitable for convincing new players to join.
- Similar logic needs to be considered for thumbnail personalization. A high QPTR thumbnail for new users might be very different to a high QPTR thumbnail for existing users. Some way to select the intent here (new vs existing) would be good. Perhaps a completely new tab where I can upload thumbs for the specific purpose of showing existing users.
It would be nice to know what a “good” qPtr is, unless that’s visible somewhere, I can’t really tell if my thumbnail is performing well compared to thumbnails from other games. And it seems to be very different based on how popular the game is. Or is that the “Unique User Qualified Play Through Rate (Recommendations)” from experience overview? But then why is the number so different from the qPtr on the thumbnails? I find this all very confusing.
Suggestion: Make the thumbnail personalization visible from the Experience page, it’s annoying having to swap between them all the time.
Hey @here, we just made a new post with 5 tips to get the most out of thumbnail personalization. Check it out here and give us more feedback on how to make the product even better: 5 Tips From Roblox Staff to Get the Most Out of Thumbnail Personalization