Predicting consumer behaviour, advanced analytics

New Zealand
New Zealand New Zealand
Consumers make most of their payments by internet banking
  • 74%
  • 70.5%
  • 54.5%
  • 46.5%
  • 39.6%
  • 40.7%
  • A higher percentage make payments via internet banking to banks and insurance companies, telcos, and retailers, respectively, compared to the regional average
  • Impact: Anti-fraud capabilities critical to the increased digital transaction frequency and customers’ trust in banks
Australia Australia
Consumers are most satisfied with the post-fraud service of banks and insurances companies
  • More than 70% satisfaction rate compared to 59.7% on average
  • Impact: Increased trust in BFSIs
Indonesia Indonesia
Consumers that encountered most fraud incidents in the past 12 months

AP Average

  • 49.8% have experienced fraud at least once compared to 34.7% on average
  • Impact: Overall anti-fraud capabilities need improvement
Singapore Singapore
Consumers have the highest trust towards government
AP Average
  • 75.5% choose government agencies, compared with 51.7% on average
  • Impact: Trust of personal data protection is centered around government agencies
Vietnam Vietnam
Consumers encountered most fraud incidents in retail and telco during the past 12 months
  • 55%
  • 54.5%
  • 32.8%
  • 35.2%
  • 55% and 54.5% have experienced fraud at least once in retail and telco, respectively, compared to 32.8% and 35.2% on average
  • Impact: Overall anti-fraud capabilities need improvement
Thailand Thailand
Most Thai consumers believe speed and resolution are severely lacking (response/ detection speed toward fraud incidents)
AP Average
  • 60.5% think it is most important, compared to 47.7% on average
  • Impact: Response time as one of key factors to fraud management to retain customers and gain their trust
India India as standalone
Consumers have the largest number of shopping app accounts in the region
  • Average of three accounts per person
  • Impact: Highest exposure to online fraud
Hong Kong
Hong Kong Hong Kong
The least percentage of consumers with high satisfaction level toward banks and insurance companies’ fraud management
AP Average
  • Only 9.7% are most satisfied compared to 21.1% on average
  • Impact: effective response towards fraud incidents to be improved
China China
Consumers are the most tolerant toward submitting and sharing of personal data
AP Average
  • 46.6% compared to the AP average of 27.5% are accepting of sharing personal data of existing accounts with other business entities
  • Impact: higher exposure of data privacy and risk of fraud
Japan Japan as standalone
Consumers most cautious on digital accounts and transactions
50.7% Actively maintain digital accounts’ validity
27% AP Average
45.5% Do not do online bank transfers
13.5% AP Average
  • More than 70% did not encounter fraud incidents in past 12 months, compared to 50% on average
  • Impact: Relatively low risk of fraud

Unravelling the art of predicting consumer behaviour

Unravelling the art of predicting consumer behaviour

In this article we will look at how predicting consumer behaviour can support an organisation's customer acquisition strategy. This follows our previous article, How to find new customers with a personalised engagement strategy, where we looked at how personalisation could improve your communications effectiveness.


The building blocks of customer acquisition


Many organisations struggle to know where to begin with understanding the behaviours and preferences of their customers. Typically, vast quantities of customer data sits in silos across various departments within an organisation, making it very hard for those organisations to plan their customer acquisition effectively.


Data profiling (as covered in our previous article) is a great place to start when organisations are looking to grow their customer numbers. By grouping all their customer data together and analysing it to identify trends and patterns, organisations start to build the insights needed to make future targeting decisions.


Data enrichment is a key element of data profiling and enhances the insights organisations can gain from their data. Appending thousands of extra data elements onto their customer data gives organisations a deeper understanding and a clear competitive advantage.


Organisations gain a lot from profiling their data to this level. The ability to segment their customer data into clear audience groups means a deep understanding of those groups and their behaviours and preferences. Organisations can then decide how and when to best communicate with those groups.


Technological advances has then enabled us to take this a step further and start to predict consumer behaviours so we can build a more agile and effective customer acquisition strategy.


Boost customer acquisition with predictive modelling


Many organisations will be fluent in building predictive models. Finance, in particular, is a department that will be adept at modelling out future scenarios in order to make decisions. The same goes for your customer acquisition strategy. By modelling out future predictions organisations can build a proactive strategy to grow their customer base.


Here are a few of the outcomes predictive modelling of consumer data can support:

  • Customer retention - predict which customers are most likely to leave your business and build a strategy to keep them, or decide which ones are not worth keeping.
  • Customer lead scoring & acquisition - Identify which prospects are most likely to take up your products and services so you can expand your bottom line
  • Identification of the ‘next best action’ - Predict which customers represent a cross-sell opportunity, and which product they are most likely to respond to
  • Store location intelligence - Predict where a new store should be opened or the impact of closing an existing one
  • Product and service pricing - Determine the optimal price point for your offering to be most competitive in the market
  • Risk insights - Identify those customers that are most likely to represent a repayment risk and build out plans to proactively support them


How predictive modelling of consumer data works


Experian Predict brings together our market leading data assets and analytical expertise to create predictive models that give you the ability to understand your customers in more detail and fine tune your acquisition strategy across key areas, such as audience profile, behaviours, and propensity to buy or churn.



Read full article

Sound interesting? Follow us for regular, published insights


By Experian 08/02/2021

Related Articles

Experian Mosaic – how consumer classification works and why it’s so powerful
Experian Mosaic – how consumer classification works and why it’s so powerful

Our award-winning, privacy compliant, consumer segmentation solution, Mosaic, powers many of the insights our clients use to drive their marketing and analytics success.

Learn more
Being Adaptable
Being Adaptable

Learn more in our insights article about the best segmentation models. How they adapt to lifestyle changes, and maintain themselves as a long-term effective segmentation solution.

Learn more
Millennial Audience Identification;</br> 9 unique segments
Millennial Audience Identification;
9 unique segments

In a world of fast paced change, people born twenty years apart won’t all behave the same. The world was different in 1980 compared to 2000, and as such, communicating…

Learn more

    We’ll analyse your existing customer data to uncover insights.


    Leverage our powerful consumer data through Mosaic and ConsumerView to learn more about your existing customers.


    Qualify the potential opportunities uncovered, whilst driving incremental spend from existing customers.


    Determine the optimal communication channels with customers and prospective customers that can potentially improve retention, cross sell and acquisition rates.


    Pinpoint the right customers and communicate with them in the most relevant ways, through the right channel at the right time with the right message.

Experian’s predictive models are uniquely developed to support your specific business goals and can work in harmony with existing models in operation within your organisation.


Dive deeper, grow faster


Predicting changes in consumer behaviour before they happen (and before the competition!) will help organisations to find new customers, adapt to changing environments proactively and grow faster. Leveraging Experian’s predictive modelling capability saves both time and the resource drain of scaling predictive models in-house.

Please complete the form below to submit a request. We will ensure a member of our team is in touch shortly.

  • Submit
By providing your personal information you agree that we may collect and process it in accordance with our Privacy Statement.