Master RAN engineering analytics

with the fewest lines of code
the least amounts of data
the simplest algorithms
and the cleanest visualisations



Digital RAN

Overview of RAN configuration analytics, data transformation, the necessity of engineering participation and the key attributes of building a RAN use case.



Comprehensive classroom/online training for developing RAN analytics capability and using Machine Learning to solve complex RAN configuration problems. 


RAN Data Science

Data science practices in RAN engineering from problem definition to solution delivery and communications.


Despite being technology-centric, it feels as if telecoms has fallen behind. 
We’ve been sold “digital transformation” from the top down but legacy processes continue to dominate. 

5G may bring huge benefits but it also comes with significant complexity. 


In most telco environments we’ve worked in, all appear held back by modern tooling designed by legacy thinking.

We propose a more nimble human-centric approach, one that has worked well for digital native companies.




Part 1 : Understanding RAN data for analytics
Data building blocks, transformation and indexing

Part 2 : Transforming RAN optimisation use cases
How to convert RAN use cases into no-code data driven options

Part 3 :  Network modelling
Representing and validating the current network planning architecture

Part 4 : Feature engineering
Creating and establishing RAN features for suitable feature engineering for input into machine learning models

Part 5 : RAN Machine analysis
Using feature engineering and machine learning algorithms to rank and score RAN

Part 6 : Classification, recommendation and prediction
Selective application for different use cases from load balancing to baseband utilisation

Part 1 : Data transformation
Handle RAN data from Huawei, ZTE, Nokia and Ericsson efficiently and economically.

Part 2 : Data joining
Once we transform data, we need to find ways to connect different pieces of information from a vast dataset at the lowest expense

Part 3 : Data visualisation
How to effectively visualise RAN data for fast analysis

Part 4 : Data engineering
Controlling and managing data flow

Part 5 : Feature engineering
Designing data for Machine Learning feature engineering

Part 6 : RAN model building
Developing use-case capability for analysing and solving machine models.