Skip to main content

The SKAdNetwork



SKAdNetwork (StoreKit Ad Network) is Apple’s system for measuring ad performance on iOS in a privacy-preserving way—introduced as part of the shift away from user-level tracking after App Tracking Transparency.

It’s basically Apple’s answer to:

“How do advertisers know an ad worked without tracking the person who saw it?”



1) The core idea

Instead of telling advertisers:

“User X saw ad Y and installed app Z”


SKAdNetwork only tells them:

“An install happened, attributed to ad campaign Y”


…but:

• no personal identity

• no device ID (like IDFA)

• no cross-app tracking data


So it’s aggregated, delayed, and anonymised attribution.



2) How it works (step-by-step)


Step 1: Ad impression / click

A user sees or clicks an ad inside an app on iOS.

The ad network registers:

• campaign ID

• ad network ID

• basic metadata

But not the user identity.


Step 2: App install happens

If the user installs the advertised app within a time window, iOS records:

“This install is associated with campaign X”


But again:

no user-level data is shared


Step 3: Apple signs the attribution

iOS generates a signed postback (a cryptographically verified message).

This is sent to the ad network with:

• campaign ID

• conversion value (limited info)

• coarse timing (delayed)

No device identifiers included.


Step 4: Delayed reporting

Reports are intentionally delayed (often hours to days) and sometimes randomised.


This prevents:

real-time tracking of individual behaviour

correlation of events back to a specific person


3) What advertisers actually get

They receive:

• number of installs per campaign

• limited conversion signals (e.g. whether user opened app, made purchase category-level signals)

• rough timing buckets


They do NOT get:

IP address

device ID (IDFA)

precise user journey

cross-app identity


4) What “conversion value” means

SKAdNetwork allows a small encoded number called a conversion value.


Apps can use it to signal things like:

• user opened app

• completed onboarding

• made a purchase tier (very limited encoding space)


But:

• it’s heavily compressed

• not user-specific

• not real-time


5) What SKAdNetwork breaks

It removes or weakens:


❌ User-level attribution

No more “this specific user clicked ad and bought product”


❌ Cross-app tracking

No linking behaviour across multiple apps


❌ Real-time feedback loops

Advertisers can’t instantly optimise based on live user behaviour



6) What still works (important)

Even with SKAdNetwork:

✔ Campaign-level optimisation

Advertisers can still see:

which ads perform better overall


✔ Aggregate performance tracking

installs per campaign

rough ROI estimation


✔ Model-based inference

Companies like Google and Meta Platforms use:

statistical modelling

cohort analysis

machine learning prediction

..to fill in the gaps.


7) Why it’s controversial in ad tech

Advertisers dislike SKAdNetwork because it:

• removes user-level visibility

• reduces precision targeting

• slows feedback loops

• makes optimisation harder


Privacy advocates like it because it:

• prevents surveillance-style tracking

• reduces identity leakage

• enforces aggregation


8) The big tradeoff

SKAdNetwork is built on a simple principle:

“Advertisers can know what worked, but not who you are or what you did specifically.”


So it shifts advertising from:

individual tracking → aggregate measurement



Summary

SKAdNetwork is Apple’s privacy-preserving system that lets advertisers measure campaign performance on iOS without exposing user identity or enabling cross-app tracking.



How advertisers “hack around” its limits using modelling and server-side signals


Okay, so they don’t “hack” SKAdNetwork in the illegal sense—what they do is reconstruct missing detail using statistical modelling, server-side data, and correlation tricks. The effect is that they recover some of the lost signal from SKAdNetwork and App Tracking Transparency, but only probabilistically.


Here’s how that actually works.



1) The big shift: from user data → prediction

After iOS privacy changes, advertisers lost:

• device IDs (IDFA)

• direct user-level attribution

• real-time conversion feedback


So they switched to:

“We don’t observe the user—we infer what likely happened based on patterns.”


This is called probabilistic attribution modelling.



2) Conversion modelling (filling in SKAdNetwork gaps)

SKAdNetwork only gives:

• campaign-level installs

• delayed, aggregated signals

• limited “conversion values”


So advertisers build models that guess missing detail.


How it works:

They train models using:

• historical pre-ATT data (when tracking was richer)

• current SKAdNetwork aggregates

• known campaign performance patterns


Then they predict:

• which users likely converted early vs late

• which campaigns likely drove high-value users

• expected lifetime value (LTV) distributions


So instead of:

“User X bought item Y”


They get:

“This campaign likely produces high-value users at a rate of ~Z%”



3) Server-side tracking (the biggest workaround)

Instead of relying on the phone to send data, companies move logic to servers.


Example flow:

User clicks ad in an app

They land on a website or app backend


The server logs:

• click timestamp

• campaign ID

• session behaviour

• purchase or signup happens on server


Server tries to match events using:

timing correlation

campaign parameters

probabilistic identifiers


This is called server-side event tracking.


It avoids iOS restrictions because:

• data is collected by the advertiser’s server, not the device OS



4) “Click-through reconstruction” (timing correlation)

Even without user IDs, advertisers exploit timing patterns:


If:

Ad click happens at 10:01

App install occurs at 10:03

Purchase occurs at 10:08


They infer:

• likely same user journey


SKAdNetwork intentionally introduces delays and noise to reduce this, but modelling still extracts trends.



5) Fingerprint-assisted probabilistic linking (limited but still used)

Even though Apple restricts fingerprinting, some weak signals remain:

• IP region consistency (not exact identity)

• device model distributions (e.g. iPhone 14 users behave differently than iPhone SE users)

• app version + OS version combinations

• session timing patterns


These are used not to identify individuals, but to improve:

“Which cluster of users likely converted?”



6) Cohort and aggregate inference (very important)

Instead of tracking individuals, advertisers build cohorts:


Example:

“Users acquired from TikTok ads in UK, iOS 17, last 7 days”


Then they measure:

• install rate

• retention

• revenue distribution


They compare cohorts across campaigns to optimise spending.


This works even with SKAdNetwork because:

SKAdNetwork still provides aggregate outputs per campaign



7) “Conversion value mapping” tricks

Apps encode behaviour into SKAdNetwork’s limited conversion value field.


Example encoding:

0 = installed only

1 = opened app

2 = completed onboarding

3 = added to cart

4 = purchased


Advertisers then:

• decode patterns across campaigns

• estimate funnel drop-off rates

• reconstruct partial user journeys statistically


It’s lossy, but still useful at scale.



8) Machine learning reconstruction (the real engine)

Big platforms like Google and Meta Platforms use ML models that:

• ingest SKAdNetwork aggregates

• combine with historical user-level datasets (pre-ATT)

• simulate likely user journeys

• adjust predictions in real time


The result is:

synthetic reconstruction of user behaviour patterns


Not exact tracking—but very effective forecasting.



Identity stitching still happens (just differently)

Even with ATT, identity resolution still exists via:


A) Logged-in accounts

Facebook / Instagram / Google accounts remain strongest identifiers


B) First-party data

websites collect emails, purchases, phone numbers

then upload hashed identifiers to ad platforms


C) Offline-to-online matching

loyalty programs

email signups

purchase receipts


These become anchors that reconnect probabilistic data.



The key limitation (important reality check)

All of this “workaround” tracking:

• is less precise than old IDFA-based tracking

• introduces uncertainty

• works best in large-scale aggregate systems, not individual certainty


So the system shifts from:

“we know exactly who did what”

to:

“we’re highly confident this type of user did this thing”



Summary

After SKAdNetwork and App Tracking Transparency, advertisers didn’t stop tracking—they switched to:

server-side event collection + probabilistic modelling + cohort analysis to reconstruct user behaviour indirectly rather than directly.

Labels:

Comments

Post a Comment

Popular posts from this blog

Point Nemo: The Most Isolated Place on Earth

Imagine standing in the middle of the ocean. There is no island on the horizon. No coastline. No lighthouse. No passing fishing boat. In every direction, land is thousands of kilometres away.  You are closer to the emptiness of the Pacific than to almost anywhere inhabited by humans. This place exists. It is known as Point Nemo — the oceanic pole of inaccessibility — and it lies in the remote South Pacific Ocean. But Point Nemo is more than simply a dot on a map. It is one of the strangest geographical locations on Earth, a place where isolation becomes almost absolute. And, remarkably, it has also become associated with something rather unusual: the final resting place of spacecraft. Where exactly is Point Nemo? Point Nemo lies at approximately 48°52.6′S, 123°23.6′W. According to NOAA, the nearest land is roughly 2,688 kilometres away. Three pieces of land are approximately equally distant: Ducie Island in the Pitcairn Islands, Motu Nui near Easter Island, and Maher Island off Ant...
Post a Comment
Read more

Why Is England Still Dumping Sewage When It Isn't Raining?

If storm overflows are designed to deal with rainwater overwhelming the sewage system, why are they sometimes discharging when there has been little or no rain? In 2025, England recorded 291,492 monitored storm-overflow spill events. At first glance, that number is shocking. It works out at almost 800 recorded spill events every day of the year. Yet 2025 was an unusually dry year. In fact, the Environment Agency says the fall in sewage-spill numbers compared with 2024 was heavily influenced by those unusually dry conditions. Spill events fell by 35%, while the total duration of spills fell by 48%. So here's the obvious question: If dry weather reduces sewage spills, why are sewage overflows operating at all when it isn't raining? The answer is complicated — and potentially far more concerning than the headline numbers suggest. What is a storm overflow actually for? To understand the problem, we need to look underground. Many parts of England still have combined sewer systems. ...
Post a Comment
Read more

Could Earth Once Have Had a Completely Different Climate?

We tend to think of Earth's climate as something relatively stable. There are warm places. Cold places. Wet places. Dry places. Ice at the poles. Deserts near the tropics. Forests covering parts of the continents. It feels permanent because human civilisation has existed for such a tiny fraction of Earth's history. But zoom out. Earth is not climatically stable at all. Over billions of years, our planet has moved between conditions that would be almost unrecognisable to us. There have been periods when ice reached surprisingly low latitudes. There have been times when Antarctica supported forests. There have been enormous changes in atmospheric composition. There have been episodes of extreme greenhouse warming. And there have been periods when much of the planet may have been covered in ice. The Earth we know today is only one possible climate state. So how different can our planet actually become? The Earth has never had just one climate Climate isn't determined by temper...
Post a Comment
Read more

Does Wearing a Mask Affect Facial Recognition? (UK Guide, 2026)

Face masks became widespread during the COVID-19 pandemic, and many people noticed something unexpected: facial recognition systems often struggled to identify masked faces. But in 2026, things have changed. So—does wearing a mask still affect facial recognition? 👉 Short answer: Yes, masks reduce accuracy—but they no longer stop recognition reliably. This guide explains how it works, what has changed, and what to expect in real-world UK use. How Facial Recognition Works Facial recognition systems analyse key features of your face and convert them into a biometric template. These typically include • Distance between the eyes • Shape of the cheekbones • Structure of the nose • Jawline and chin • Skin texture patterns This data is then compared against databases to find a match. What Happens When You Wear a Mask? A standard face mask covers: • Nose • Mouth • Lower cheeks This removes a large portion of facial data—especially areas older systems relied on. Early Impact: Why Masks Used to ...
Post a Comment
Read more

Could Earth Have Once Had a Ring Like Saturn?

Look at Saturn and it is difficult not to wonder what Earth would look like with rings. A vast band of ice and rock stretching across the sky. A permanent feature visible from the surface. Shadows moving across the planet as the ring system changed with the seasons. It sounds like science fiction. But Earth may actually have had something resembling a ring system in its distant past. Not necessarily a beautiful, permanent structure like Saturn's — but a temporary ring of debris could have formed around our planet after a massive collision. And the most intriguing possibility is that such an event may have played a role in creating the Moon. Earth wasn't always the quiet planet we know today The young Solar System was a chaotic place. Planets were still forming. Asteroids and planetary embryos were moving through unstable orbits, occasionally crossing paths. Collisions were not unusual. Some were relatively small. Others were catastrophic. The leading explanation for the Moon...
Post a Comment
Read more

When Banks Become Landlords, Who Gets Left Out?

For generations, banks have made money from Britain's housing market by lending people the money to buy homes. Now something different is happening. Some banks are beginning to buy and hold residential property themselves. And that raises an uncomfortable question: What happens to house prices when the institutions that finance the housing market also start competing with the people trying to buy the houses? From financing homes to owning them The most prominent example in Britain is Lloyds Banking Group. Through its Lloyds Living operation, the banking group has built a substantial portfolio of residential properties.  Its portfolio has grown to more than 7,500 homes, and in July 2026 Lloyds Living agreed a further acquisition of 980 suburban homes across 14 developments. These aren't simply properties on which Lloyds has issued mortgages. They are part of a residential investment and rental business. That distinction matters. A bank providing a mortgage helps an individual be...
Post a Comment
Read more

Who Is Really Behind the News You See on Social Media?

Scroll through Facebook, X, TikTok or Instagram and you can encounter hundreds of accounts presenting themselves as news. Some look remarkably professional. Others appear to be little more than a logo, a dramatic headline and a constant stream of political stories. They may call themselves independent media. Alternative media. Citizen journalism. Breaking news. But who actually runs them? Who owns the website behind the Facebook page? Who registered the company? Who are its directors? Who pays for the operation? Who controls the advertising? And are several apparently independent news outlets actually connected to the same people? In an age when a social-media post can reach hundreds of thousands of people within hours, these questions have become increasingly important. And surprisingly often, the answers are publicly available. The brand may not tell you much One of the easiest mistakes to make is to treat a media brand as though it were a person. A page might have a name suggesting ...
Post a Comment
Read more

GRB 080319B: The Explosion We Could See Across Half the Universe

On 19 March 2008, something extraordinary happened in the distant universe. A massive star died. The event produced an enormous explosion known as a gamma-ray burst, releasing an incredible amount of energy into space. But there was something particularly unusual about this one. For a brief period, the explosion was bright enough to be seen from Earth with the naked eye. The remarkable part? The explosion happened roughly 7.5 billion light-years away. By the time its light reached Earth, our planet had travelled through billions of years of cosmic history. Civilisations had risen and disappeared, continents had shifted and species had evolved — while the light from this distant catastrophe was still making its way towards us. Astronomers named it GRB 080319B. It became known as the "Naked-Eye Burst." A flash from the distant universe Gamma-ray bursts are among the most violent events known to occur in the universe. They are extraordinarily brief, but can release enormous amou...
Post a Comment
Read more

Did Ice Age Humans Retreat Underground to Survive the Cold?

Could some of our ancestors have spent far more of the Ice Age beneath the surface than we realise? When we imagine humans during the Ice Age, we tend to picture hunters crossing frozen landscapes, wrapped in animal skins, tracking mammoths and reindeer across windswept plains. It's an image that has become almost synonymous with prehistoric humanity. But there is another possibility. When conditions became brutally cold, perhaps the smartest place to be wasn't out on the frozen landscape at all. Perhaps it was underground. Humans have been using caves and rock shelters for hundreds of thousands of years. We know that Neanderthals, Denisovans and Homo sapiens repeatedly occupied caves, sometimes during extraordinarily cold climatic periods. But this raises a more intriguing question: Did some human groups retreat into underground environments for much longer periods during the most severe phases of the Ice Age? The answer isn't as straightforward as it might first appear. W...
Post a Comment
Read more

What If Consciousness Isn't Produced by the Brain?

You are reading these words. You can hear sounds around you. You can remember yesterday. You can imagine tomorrow. You can feel pain, recognise a face and wonder what it means to be alive. All of this feels completely ordinary. But scientifically, it is extraordinary. Somehow, electrical and chemical activity inside roughly three pounds of biological tissue is associated with the experience of being you. We know an enormous amount about the brain. We can observe neurons firing. We can map brain regions. We can measure electrical activity and watch networks communicate. We can even manipulate brain activity and change perception, memory and behaviour. And yet one enormous question remains: Why is there an experience at all? The brain clearly matters Before going further, there is an important distinction. There is overwhelming evidence that consciousness is intimately connected to the brain. Damage particular brain systems and consciousness can be profoundly altered. Anaesthesia can rev...
Post a Comment
Read more