Increasing revenue and customer satisfaction by implementing behavioral scoring

Telecommunication industry use case

Background Story

MobiCom Corporation is the largest mobile phone operator in Mongolia. It was established as a joint Mongolian-Japanese venture on 18 March 1996 to be the first Mongolian cell phone service. It was founded by Newcom Group, Sumitomo, and KDDI. As of June 2015, Mobicom holds over 33 percent of the mobile service market, with network coverage of 95 percent across the country, the broadest coverage in Mongolia. It delivers its services through 64 branch units, 2,200 dealers, and over 10,000 mobile sales points.


Prepaid vs. Postpaid

For companies like MobiCom, there are usually two types of customers, prepaid and postpaid. On a prepaid plan, customers pay for their phone service upfront. On a postpaid plan, they pay at the end of the month based on their usage. From the business perspective, they often try to move their prepaid customers to postpaid due to its higher average revenue per user (ARPU) and the nature of assured revenue of postpaid customers. However, with postpaid plans, there is a risk of payment defaults by the customer. Due to this, telecom companies need to assess, identify, and target customers with a lower risk of defaulting their monthly payments. This is where our scoring comes in.

Behavioral scoring

When implementing our scoring models, given that MobiCom was already integrated with the credit bureau, we used credit history as a baseline rule and incorporated it into a modeling structure. We used various internal data types, including monthly average usage, payment history, tendencies, and device information, etc. Upon researching and analyzing the customers’ existing data, we prepared the data for modeling by selecting and extracting relevant features. We ranked the features based on the importance and removed some of the insignificant ones while creating new features based on the ones that can be summarized and represented.


  1. Fast and easy approval process enabled by the fully automated scoring system.
  2. Higher customer satisfaction with the hassle-free onboarding
  3. Revenue increase as more customers moved to a postpaid plan
  4. Reduced operational cost for driving customers to opt for postpaid

And Solutions' Credit Scoring Solution

Data Collection

Direct questionnaires
User profiling and demographic data collection through direct questionnaires to customers via multiple mediums.

Device information
Device information such as manufacturing date, price, phone calls, contact information, application data, etc., can serve as an additional and accurate data stream.

Third-party data sources
Along with the data from credit bureaus, banks, and other financial institutions, third-party data such as telephone data, utility bill data is also collected to have a better and more accurate look into the customers’ behavioral tendencies.

Data Analysis

Data structuring
Collected data is sanitized and stored with the desired structure for efficient data operations.

Data labeling
Tagging the raw data with one or more contextual attributes for use in model training.

Feature selection and extraction
Identifying, manifesting, and ranking dataset features that make the most sense of data based on accuracy and sensitivity.

Model Training

Our scoring solution uses multiple AI/ML algorithms such as Random Forest, Artificial Neural Network, KNN, etc., based on the business objectives, goals, and nature. It then creates an ensemble model consolidating results from the utilized models.

Self-learning and updating

The active learning model works continuously and is fed with new data sets for supervised/unsupervised learning to make the system more intelligent and accurate.


Our base gamification schema with a loyalty system helps businesses access and identify desirable customers by generating key features that are highly suitable for modeling.