Traffic analytics and reporting for operators, ISPs and regulators
DPI traffic analysis and reporting for telecom operators
DPI traffic analysis turns classified traffic into reports that teams can act on: which applications fill the network, how each class is trending, and what each policy did. Interkey Intelligent DPI classifies traffic in real time, including encrypted flows, without decrypting them, and presents the results in Live View. Live View starts from a network-wide view and drills down to application and flow level, shows network- and application-level trends and gives real-time policy execution feedback, with latency measured in seconds.
A Saudi product, built by Interkey
For capacity planning, network operations, policy and regulatory affairs teams at telecom operators and ISPs, and for regulators. Reviewed November 2026.
- What is reported:metadata about applications, traffic volumes and triggered policies, not the content of traffic.
- How deep it goes:from the network-wide view down to application and flow level, with trends at network and application level.
- What it closes:real-time policy execution feedback shows whether each policy is doing what it was approved to do.
- Who controls the data:retention and access follow your data-governance rules and the contract, and the platform can run entirely in the Kingdom.
Why DPI traffic analysis goes beyond volume reports
Most operators already report how much traffic crosses each link, cell and gateway. A volume report cannot say what that traffic is, so capacity plans, policy reviews and regulatory submissions all rest on an incomplete picture. DPI traffic analysis adds the missing dimension: each flow is assigned to an application or protocol class, and reports are built on those classes.
That only works if classification holds up where traffic is hardest to read. Encryption removes the payload signal, and many applications share the same common ports. Interkey Intelligent DPI classifies from flow behaviour (handshake structure, packet sizing and timing, and endpoint behaviour) rather than from port numbers or payload alone, so encrypted and tunnelled traffic is reported by class instead of disappearing into "unknown".
What Live View shows
| View | What it shows | Typical question it answers |
|---|---|---|
| Network-wide traffic view | Traffic across the network, with drill-down to application and flow level | What is on the network right now, and where? |
| Trend analysis | Network-level and application-level trends | Which classes are growing, and since when? |
| Policy execution feedback | How policies are executing, in real time | Is each policy doing what it was approved to do? |
| Reporting latency | Measured in seconds, not minutes | Can operations teams see a change while it is happening? |
Live View results also feed back into the platform to refine models and policies. See Live View on the features page.
What each team gets from DPI reporting
| Team | What the reports give them | Related decision |
|---|---|---|
| Capacity planning | Application-level trends showing which classes drive load, where and when | Where to add capacity, and when |
| Network operations | A network-wide view with drill-down when something changes | Whether a change in load needs action |
| Policy and product | Policy execution feedback and the traffic each policy triggered on | Whether a rule needs adjustment |
| Regulatory affairs and compliance | A reporting layer that describes traffic by application class | What to report, and how to support it |
| Management | Trends by application class across the network | Investment and service priorities |
For the congestion case in detail, see Mobile network congestion: diagnose it by application.
Reporting by class, not by person
DPI reporting is built for network governance and regulatory compliance, not for surveillance of individuals. The output is metadata about applications, traffic volumes and triggered policies; encrypted content stays encrypted. Policies act per application, subscriber group or cell.
Put these rules in writing before reports go live:
1. Purpose.Which decisions each report supports: capacity, operations, policy, regulatory reporting.
2. Aggregation.The level at which each team sees data, starting from application classes and subscriber groups.
3. Retention.How long each type of metadata is kept, set by your data-governance rules and the contract.
4. Access.Who can query which views, and how access is reviewed.
5. Location.Where the data sits. The platform runs on your infrastructure and can operate entirely in the Kingdom.
Questions to ask about any DPI reporting layer
- How accurate is classification for the classes in my reports, measured on my own traffic and including false positives?
- How much of my traffic ends up as "unknown", and how is that shown?
- How quickly does a change in traffic appear in the reports?
- Can I see whether a policy executed as intended, not only that it exists?
- What data is kept, for how long, who can see it, and can it all stay in the Kingdom?
- How do reports reach the systems my teams already use? Agree this during scoping and document it in the integration plan.
Interkey's product material states 99% recognition accuracy, including for VPN and other adversarial encrypted applications. The figure has not been independently benchmarked and is not a specification for any particular network, so measure it on yours. See Measuring DPI classification accuracy on your traffic.
Out-of-band is enough for reporting
Reporting does not need the platform in the forwarding path. Out-of-band, it receives a copy of traffic and classifies and reports without touching the service path, which is where most operators start. An inline deployment is needed only when policies must act on traffic, usually as a second phase. See Inline vs out-of-band DPI: choosing the deployment.
The platform is designed for traffic intake at terabit-per-second scale across fixed and mobile networks. Throughput for your network is scoped per deployment.
Check the reports on your network in 3 stages
1. Written acceptance criteria.Agree which reports matter, on which traffic, how they are checked and what counts as a pass.
2. Out-of-band classification against verified traffic.Compare the reports with traffic you have verified, and measure false positives as carefully as detection.
3. Report-only policy, then the inline decision.Use policy execution feedback to see what each rule would have done before anything acts on traffic.
See also: How Interkey runs a DPI proof of concept
Questions about DPI traffic analytics
What is DPI traffic analysis?
Does it read the content of traffic?
Do we need an inline deployment to get reports?
How current are the reports?
Who decides what data is kept?
How is it priced?
Related pages
- Network traffic management for telecom operators
- Network traffic classification engine for telecom operators
- Encrypted traffic classification without decryption
- Interkey Intelligent DPI features
- Deep packet inspection for Saudi telecom networks
- Telecom subscriber analytics
- Quality of experience monitoring
Proof of concept in three phases
Written acceptance criteria.Agree which rules are tested, on which traffic and subscriber groups, how results are measured and what counts as a pass.
Out-of-band classification against verified traffic.Measure false positives as carefully as detection for every class the rules depend on.
Report-only policy, then the inline decision.Each rule shows what it would have done; enforcement follows only after classification has proven itself.
Discuss DPI reporting for your network
Tell us which teams need traffic reports (capacity, operations, policy, regulatory), what you report today, whether your network is fixed, mobile or both, and your timeline. Our team in Riyadh replies in Arabic or English.
- Our engineers read your request
- We agree the scope of a technical session
- You see the product on a use case you choose