Ai Video: Learning from data and curbing e-commerce fraud

1st July, 2019

E-commerce companies, including the ones from the travel sector, are gradually focusing on deploying a multi-disciplinary approach, combining different technologies (including both supervised and unsupervised machine learning) to combat fraud.

Unsupervised models don’t have clearly labelled data, while supervised models do.

As a specialist, Nethone asserts that machine learning today is letting companies deal with fraud. For instance, friendly fraud by helping discover which aspects of customers’ behaviour and transactions designate friendly fraud.

Overall, favourable results come from the ability to experiment with various machine learning-based methods, trying variations on them and testing them with a variety of data sets. It is fascinating to assess how machine learning automates the extraction of known and unknown patterns from data.

Supervised machine learning relies on historical data to predict and prevent further possibilities of fraud based on past fraud. The data set is labelled based on previous observations of fraud, and is described as either fraudulent or genuine. Unsupervised machine learning can be used to learn on the fly and identify fraudulent patterns even without having been trained with historical data, i.e. able to identify unknown fraud attacks. 

Rodrigo Camacho, Chief Commercial Officer, Nethone, referred to the role of unsupervised learning in managing friendly fraud and criminal fraud. “(One) looks at the entirety of the dataset (without a label). Then cluster transactions into different bubbles. These clusters are correlated with a type of fraud, for instance, friendly fraud or criminal fraud,” said Camacho. And from here on companies can work on strategies for e-commerce, work on association with key players such as acquirers and issuers etc. for mitigating the risk.

Specialists recommend that merchants should rely on both supervised and unsupervised machine learning to comprehend both the historical patterns of use, as well as identify anomalies. 

By Ritesh Gupta

Check upcoming Ai Conferences dates

Follow Ai on Twitter: @Ai_Connects_Us

 

Editorials

  • Ai Editorial: Working on apt approach to combat mobile commerce fraud +

    14th September, 2019 Ai Editorial: The behaviour of consumers when they shop via mobile and what makes such devices risky has to be ascertained. It is must to focus on Read More
  • Only 1 in 3 travel merchants expected to be SCA-ready: report +

    9th September, 2019 The travel industry at large isn’t ready for the implementation of Strong Customer Authentication (SCA), required for all online transactions in Europe from 14 September 2019.   Read More
  • Ai Video: Is the 21/20/20 target for NDC feasible? +

    5th September, 2019   IATA’s NDC standard is under constant scrutiny – how far it has come and how far it still has to go? This week, as shared by Read More
  • 1
  • 2
  • 3
  • 4
  • 5