H2O.ai Case Studies More Accurate, Real-time Risk Score with Fast Time-to-Market

Edit This Case Study Record

	More Accurate, Real-time Risk Score with Fast Time-to-Market H2O.ai

More Accurate, Real-time Risk Score with Fast Time-to-Market

H2O.ai

Technology Category	Analytics & Modeling - Machine Learning
Applicable Industries	Telecommunications
Applicable Functions	Sales & Marketing
Use Cases	Predictive Quality Analytics
Services	Data Science Services
Challenge	Airvantage, a South African cellular telecommunication provider, was facing a challenge with its Prepaid Airtime Advance System (PAS). The system, which advances airtime, data, or mobile money to subscribers, was using a series of static business rules to make airtime advance decisions. However, these rules were overly cautious, leading to a high number of false negatives - refusing credit to desirable customers. Airvantage needed a solution that would allow them to accurately assess the risk of advancing credit to their subscribers, without unnecessarily declining potential customers. They sought a data science toolkit that could help them build a more accurate risk model, and after evaluating over 30 toolkits and platforms, they decided to use H2O Driverless AI. Read More
About Customer	Airvantage is a leading cellular telecommunication provider based in South Africa. The company operates in over a dozen countries across Africa and the Americas, offering advanced financial products and services. One of their key offerings is the Prepaid Airtime Advance System (PAS), which allows Mobile Network Operators to advance airtime, data, or mobile money to their subscribers. The system uses AI to deliver proprietary profiling and a dynamic rules engine for flexible advancing, revenue maximisation, and customer loyalty. The risk associated with advancing credit is borne directly by Airvantage, making it crucial for them to accurately assess the risk associated with each advance. Read More
Solution	Airvantage chose to use H2O Driverless AI to address their challenge. The company was impressed by H2O.ai's focus on engineering and solution-building, as well as the support offered by their team of engineers and data scientists. Using H2O Driverless AI, Airvantage was able to reduce their development cycles from weeks to hours, and built their first production model within a month of completing the evaluation. The model was deployed with live A/B testing to continue to test in-place. The ease of deployment offered by H2O Driverless AI MOJOs allowed the team to quickly tune the model to achieve the best results. The solution is currently deployed on client premises to lower costs and respect the sensitive nature of their subscriber data sets. Read More Log in to view content
Contents

Technology Category

Analytics & Modeling - Machine Learning

Applicable Industries

Telecommunications

Applicable Functions

Sales & Marketing

Use Cases

Predictive Quality Analytics

Services

Data Science Services

Challenge

Airvantage, a South African cellular telecommunication provider, was facing a challenge with its Prepaid Airtime Advance System (PAS). The system, which advances airtime, data, or mobile money to subscribers, was using a series of static business rules to make airtime advance decisions. However, these rules were overly cautious, leading to a high number of false negatives - refusing credit to desirable customers. Airvantage needed a solution that would allow them to accurately assess the risk of advancing credit to their subscribers, without unnecessarily declining potential customers. They sought a data science toolkit that could help them build a more accurate risk model, and after evaluating over 30 toolkits and platforms, they decided to use H2O Driverless AI.

About Customer

Airvantage is a leading cellular telecommunication provider based in South Africa. The company operates in over a dozen countries across Africa and the Americas, offering advanced financial products and services. One of their key offerings is the Prepaid Airtime Advance System (PAS), which allows Mobile Network Operators to advance airtime, data, or mobile money to their subscribers. The system uses AI to deliver proprietary profiling and a dynamic rules engine for flexible advancing, revenue maximisation, and customer loyalty. The risk associated with advancing credit is borne directly by Airvantage, making it crucial for them to accurately assess the risk associated with each advance.

Solution

Airvantage chose to use H2O Driverless AI to address their challenge. The company was impressed by H2O.ai's focus on engineering and solution-building, as well as the support offered by their team of engineers and data scientists. Using H2O Driverless AI, Airvantage was able to reduce their development cycles from weeks to hours, and built their first production model within a month of completing the evaluation. The model was deployed with live A/B testing to continue to test in-place. The ease of deployment offered by H2O Driverless AI MOJOs allowed the team to quickly tune the model to achieve the best results. The solution is currently deployed on client premises to lower costs and respect the sensitive nature of their subscriber data sets.

Impact #1	Airvantage is now approving thousands of additional advances every day.
Impact #2	The repayment rates comfortably exceed their targets.
Impact #3	The speed of feature development and modelling with H2O Driverless AI reduced development cycles from weeks to hours.

Impact #1

Airvantage is now approving thousands of additional advances every day.

Impact #2

The repayment rates comfortably exceed their targets.

Impact #3

The speed of feature development and modelling with H2O Driverless AI reduced development cycles from weeks to hours.

Benefit #1	10,000 more advances approved per day
Benefit #2	Advance rejections reduced by 15%
Benefit #3	Evaluation to Production in one month

Benefit #1

10,000 more advances approved per day

Benefit #2

Advance rejections reduced by 15%

Benefit #3

Evaluation to Production in one month

Download PDF Version

Overview

More Accurate, Real-time Risk Score with Fast Time-to-Market

Operational Impact

Quantitative Benefit