The Algorithms of the Algorithm [TikTok]

ReverseAndCode said:

The game could change at any time - against you @manogoyt - and a device ban may follow. TikTok changed many things recently, a famous public API service doesn't work anymore, so they may monitor your accounts already.

If you don't want to lose your earnings of the 4 accounts, you should at least buy another cheap phone to start with the 5th account. Although I still recommend iPhones for TikTok, to avoid the transmission of device data (link above).

Click to expand...

mntnrk said:

Thanks, this is so interesting, although I have no use for it, I am sure someone will.

Do you think Instagram gathers this much information as well?

Click to expand...

ReverseAndCode said:

I have to wait 28 more days to be able to upgrade to BHW Jr. VIP.

Then I'll be allowed to post some TikTok app traffic insights here (one of my posts has been removed already).

Click to expand...

Putt said:

View attachment 156373​

I got asked by @ReverseAndCode to share some info I have about the TikTok algorithm and their plans for the future. I'm going to use this thread as an ongoing opportunity to share interesting pieces of information as I see fit.

If you have any questions, feel free to ask and I'll make sure to find out the answer.

1. User Interest Vector Space Modelling
As we expected, TikTom categorizes both users and creators with 'tags' that are related to interests. I'm 99% sure that these line up with the 20 or so content tags that appear in the Creator Marketplace. Rather than using a 100% dynamic system to pick FYP content, the algorithm only searches within the scope of your 'tags'. This is how FYPs can be so different and it can be difficult to discover new types of content if you already 'trained' your FYP.

Equally, this will likely make niche shifts difficult as if you start uploading a different type of content, your reach will be pushed towards a bad audience. Something to be wary of if you're buying accounts. If you buy a sports account and start publishing gaming content, rather

2. Positive Reinforcement Weighting
The order of 'significance' for engagements (high to low) is Share, Comment, Like, Viewtime.

3. Device Data Capturing
View attachment 156368
View attachment 156369

4. Cross Domain Learning
The algorithm is set up to predict behaviour based on similar people. If you like 'A' and 99% of people who like 'A', like 'B', it will assume you also like 'B'. It also does this cross-domain. What this means is the algorithm will identify that people who like Shawn Mendes are more likely to enjoy football over baseball or whatever.

5. Pre-Publication Content Scoring
This tech was researched for the purpose of their ad platform but it is likely used or soon to be used by the main platforn. It describes machine learning algorithms that can identify the quality of a piece of content without having to show it to users to collect data. This could easily be one of the reasons behind 0 views posts. Imagine Google assigning ads a quality score instantly after creation of ad copy.

Other Stuff
View attachment 156371
View attachment 156372

More analysis + research to come...

Click to expand...

otc said:

let’s say I went and bought 10 new iphones. and bought a single sim card. Would tiktok notice that I was using the same Sim on each new account bearing in mind they are all on different fresh new iphones

Click to expand...

zodiaC- said:

Yes because it would be the same IP address if using a single SIM card

Click to expand...

Putt said:

View attachment 156373​

I got asked by @ReverseAndCode to share some info I have about the TikTok algorithm and their plans for the future. I'm going to use this thread as an ongoing opportunity to share interesting pieces of information as I see fit.

If you have any questions, feel free to ask and I'll make sure to find out the answer.

1. User Interest Vector Space Modelling
As we expected, TikTom categorizes both users and creators with 'tags' that are related to interests. I'm 99% sure that these line up with the 20 or so content tags that appear in the Creator Marketplace. Rather than using a 100% dynamic system to pick FYP content, the algorithm only searches within the scope of your 'tags'. This is how FYPs can be so different and it can be difficult to discover new types of content if you already 'trained' your FYP.

Equally, this will likely make niche shifts difficult as if you start uploading a different type of content, your reach will be pushed towards a bad audience. Something to be wary of if you're buying accounts. If you buy a sports account and start publishing gaming content, rather

2. Positive Reinforcement Weighting
The order of 'significance' for engagements (high to low) is Share, Comment, Like, Viewtime.

3. Device Data Capturing
View attachment 156368
View attachment 156369

4. Cross Domain Learning
The algorithm is set up to predict behaviour based on similar people. If you like 'A' and 99% of people who like 'A', like 'B', it will assume you also like 'B'. It also does this cross-domain. What this means is the algorithm will identify that people who like Shawn Mendes are more likely to enjoy football over baseball or whatever.

5. Pre-Publication Content Scoring
This tech was researched for the purpose of their ad platform but it is likely used or soon to be used by the main platforn. It describes machine learning algorithms that can identify the quality of a piece of content without having to show it to users to collect data. This could easily be one of the reasons behind 0 views posts. Imagine Google assigning ads a quality score instantly after creation of ad copy.

Other Stuff
View attachment 156371
View attachment 156372

More analysis + research to come...

Click to expand...

Putt said:

View attachment 156373​

I got asked by @ReverseAndCode to share some info I have about the TikTok algorithm and their plans for the future. I'm going to use this thread as an ongoing opportunity to share interesting pieces of information as I see fit.

If you have any questions, feel free to ask and I'll make sure to find out the answer.

1. User Interest Vector Space Modelling
As we expected, TikTom categorizes both users and creators with 'tags' that are related to interests. I'm 99% sure that these line up with the 20 or so content tags that appear in the Creator Marketplace. Rather than using a 100% dynamic system to pick FYP content, the algorithm only searches within the scope of your 'tags'. This is how FYPs can be so different and it can be difficult to discover new types of content if you already 'trained' your FYP.

Equally, this will likely make niche shifts difficult as if you start uploading a different type of content, your reach will be pushed towards a bad audience. Something to be wary of if you're buying accounts. If you buy a sports account and start publishing gaming content, rather

2. Positive Reinforcement Weighting
The order of 'significance' for engagements (high to low) is Share, Comment, Like, Viewtime.

3. Device Data Capturing
View attachment 156368
View attachment 156369

4. Cross Domain Learning
The algorithm is set up to predict behaviour based on similar people. If you like 'A' and 99% of people who like 'A', like 'B', it will assume you also like 'B'. It also does this cross-domain. What this means is the algorithm will identify that people who like Shawn Mendes are more likely to enjoy football over baseball or whatever.

5. Pre-Publication Content Scoring
This tech was researched for the purpose of their ad platform but it is likely used or soon to be used by the main platforn. It describes machine learning algorithms that can identify the quality of a piece of content without having to show it to users to collect data. This could easily be one of the reasons behind 0 views posts. Imagine Google assigning ads a quality score instantly after creation of ad copy.

Other Stuff
View attachment 156371
View attachment 156372

More analysis + research to come...

Click to expand...

anon568 said:

Hi ! Really helpful post, thank you, I'm doing some research about reverse engineering the tiktok algorithm to understand how to perform as a content creator, do you have any informations or research about it ?

Click to expand...

kilovats said:

The amount of data they collect is absurd

Click to expand...