Speakers at Directions 2008 explained how some of today’s leading organisations harness the power of knowledge about their customers to maximise the value they generate. Topics included how CRM and marketing departments can benefit from predictive analytics to increase marketing productivity and efficiency, reduce costs and generate a higher return on investment.
|
Clementine
Up- and cross-sell with the right offer for each customer
Ola Gustafsson
Customer data analyst
Länsförsäkringar AB
Sweden
Länsförsäkringar Alliance is the market leader in non-life insurance in Sweden, with a market share of 29 percent. The 24 regional companies service more than three million customers and co-operate through Länsförsäkringar AB. The main business challenge for the organisation is to cross- and up-sell bank and life insurance services to non-life customers. Enter predictive analytics.
With analytics, Länsförsäkringar now uses historical data to build predictive models for customer acquisition, cross-selling and churn. In this session, they explained how implementing analytics produced a dramatic increase in campaign selection productivity that led to a response rate of nine percent for a car insurance telemarketing campaign. Previously, national campaigns with several products were, at best, produced twice a year. Now, the output level is five campaign selections every day.
Länsförsäkringar now considers predictive models to be useful knowledge assets founded on real business experience; the models are also used for outbound telemarketing campaigns that yield good response rates; and the organisation is starting work on new campaigns such as churn prevention.
As a result of implementing analytics, Länsförsäkringar Alliance estimates that it receives over 800.000 inbound calls in a year, and using predictive models it is able to calculate daily best-offers for each individual customer – and present them for staff to act upon.
Back
|
Clementine, Text Mining for Clementine, Dimensions
The Predictive Enterprise at work: revealing the causes of dissatisfaction through analytics
Simon Dudley
Customer Analytics Manager
Royal & SunAlliance
UK
Royal & SunAlliance is one of the world’s leading insurance companies, writing business in over 130 countries and providing general insurance products to over 20 million customers worldwide.
This presentation discussed how Royal & SunAlliance and SPSS formed a partnership to understand better the interactions that take place across their sales, service and claims call centres, and how this insight drives operational change to enhance customers’ overall experiences.
This real-world example of the Predictive Enterprise at work described the benefits that have been realised in the areas of increased customer satisfaction; improved customer retention; and optimised operational processes through understanding the root causes of customer dissatisfaction – why people phone call centres and how many calls they make before the issue is resolved.
The session also included practical advice on how to approach this type of analysis: the challenges to expect and the lessons to be learned.
Back
|
|
SPSS, Clementine
Using data mining for more effective marketing
Christos Matsoukas
Head of Business Intelligence
EFG Eurolife
Greece
Eurolife, one of the largest insurance groups in Greece, proudly states that its aim is to provide its customers with comprehensive insurance through modern, understandable products. Recognising that each customer is unique and has distinctive needs, it offers a range of specialised but integrated solutions to suit individual cases.
Consequently, its first and most important requirement is to have a better view of its customers, allowing it to understand their needs and to devise more specifically targeted marketing campaigns.
In this session, Eurolife described how they use data mining to find common characteristics and behavioural patterns among its customers and generate customer-centric segmentations and loyalty propensity models for cross- and up-selling campaigns.
They further explained how they use multi-attribute segmentation to find products that are related to customers’ existing portfolios, and then find the right time to offer them. Eurolife has achieved considerable success with its methods, which have increased positive responses to health insurance marketing campaigns from two percent to 25 percent.
Back
|
Text Mining for Clementine
Text Mining for Clementine: overview and roadmap
Eric Martin
Product Marketing Manager
SPSS Inc.
France
This session was intended for users of Text Mining for Clementine – or anyone who wished to learn more about how to leverage analytical or predictive applications to turn unstructured information into actionable knowledge.
Attendees heard how extracted concepts and categories can be combined with structured data and applied to create models to yield better and more focused decisions using Clementine’s full suite of data mining tools. In addition, they were told about automated translation and speech-to-text capabilities that can be added to Clementine to maximise the return on investment of any predictive application.
Among other topics, the sessions discussed these new features in Text Mining for Clementine 12.0/12.0.1:
- Enhanced support for verticalisation
– New Template Editor
– Updated libraries – Sentiment Analysis, CRM, Security Intelligence, Competitive Intelligence, Life Sciences (Genomics, Mesh®), IT
- Enhanced multi-lingual capabilities
– Support of Sentiment Analysis in five Languages (Dutch, German, English, French, Spanish)
– More than 14 languages available through Language Weaver.
Back
|
|
Text Mining for Clementine
The real benefits of text mining
Rebecca Wettemann
Vice President, Research
Nucleus Research
USA
Olivier Jouve
Vice President, Corporate Development
SPSS Inc.
USA
Text mining can help companies leverage all the unstructured information they have about products, services, competitors, and customers to increase customers’ satisfaction and loyalty. SPSS Text Mining leverages SPSS’ data mining platform to enable companies rapidly to analyse unstructured information for better decision making.
This presentation about innovations in the field of text mining also heard, directly from an industry analyst, a view of the market and suggested best practices, use cases and returns achieved by SPSS customers.
Back
|
Clementine
Making a profit from customers’ calls – sell in real time
Omar Rois Merino
Customer Analysis Manager
Angelica Dominguez
Customer Analysis
DIGITAL+
Spain
Digital + is the leading pay-per-view television provider in Spain. It reaches 2,050,000 homes, giving it a total of some six million customers.
The challenge for Digital + was to improve profits by increasing the customer retention rate and the customer loyalty rate. In addition, they wanted to acquire new customers and provide better customer satisfaction through enhanced call centre operations.
To achieve this, Digital + has used SPSS to implement customer pop-up cards for its call centre agents to use as an information, segmentation and sales tool.
This session was about how these cards help call centre agents by giving them a picture of each customer, and work as a segmentation tool that makes it possible to customise the interactions and have one-to-one conversations.
Powered by SPSS Predictive Analytics, these cards provide information such as the length of the contract and the product package, and a wide variety of other data to inform and enrich the relationship between Digital + and its customers. After a two-month pilot programme, predictive call centre operations produced a 20 percent increase in the retention rate.
Back
|
|
Clementine, SPSS Predictive Enterprise Services
Building complete understanding of customers through data integration
Dag P. Svendsen
Analyst – Data Mining/Statistical Modelling
Komplett
Norway
Komplett is a leading European e-commerce player operating in 10 countries selling computer components, PCs, home electronics and related equipment to end-users and resellers. Komplett companies have close to 1,6 million registered customers.
During this session, attendees found out how, through data mining, Komplett.com is able to collect and integrate behavioural, attitudinal, and other data from several sources to get a complete understanding of its customers.
In particular, they heard how Web usage data is integrated with customers’ purchase histories, and then merged with socio-demographic and attitudinal variables from surveys.
The richness of the data resulting from this integration permits advanced predictive modelling in the development of, for example, marketing campaigns and micro-targeting. Komplett is also using modelling to make product recommendations for visitors to its Web shops.
Back
|
SPSS Server, Clementine
From insight to action with operational data – avoiding Pyrrhic marketing victories
Morgan Sandstrom
Senior Consultant
Bo Bäckman
Senior Consultant
SIFO Research International Sweden AB
Sweden
After years struggling with decreasing customer loyalty, marketers are finding that the cost of building and maintaining client relations has reached levels where sustainable profitability is threatened and their work tends to result in Pyrrhic victories.
In this paper, SIFO described a different approach based on fusing Target Group Index data with customer databases to support various marketing strategies, customer retention and cross/up selling campaigns. This makes it possible to use values, interests, activities as predictive factors.
In addition, when customer satisfaction studies are fused it is possible to direct messages selectively toward satisfied, loyal and profitable customers.
The focus of the presentation was not so much on the fusion techniques used, but on how critical operational information can be identified, and how internal and external data contribute to evaluating and handling client relations, directing marketing activities and maintaining a profitable return on marketing.
Back
|
|
Clementine
Data mining – what it really is and what it can do for your organisation
Richard Hren, PhD
Director, Product Marketing
SPSS Inc.
USA
‘Data mining’ is a frequently used yet often misunderstood technical term, and in this session talked about the ‘true’ meaning of data mining: what it is – and isn’t; what it does – and doesn’t do; and how it can integrate and inform the day-to-day decision processes of many organisations.
As importantly, the session gave an appreciation of the incredible value that predictive analytics delivers to an organisation – how the use of analytics drives better decisions to provide rapid and significant returns.
In fact, the ability to deliver impressive return-on-investment figures is the critical proof of the rationale for deploying predictive analytics and becoming a true Predictive Enterprise.
Back
|
Clementine
Constructing a robust definition for churn modelling high-value customers
Sarah Gray
Customer Insight Manager
Panyiotis Georgiou
Customer Insight Analyst
Tesco Mobile
UK
As offerings amongst competitors become increasingly rich, operators in the UK telecom industry are continuously faced with the issue of customers churning – defecting to other suppliers. The challenge for Tesco Mobile was to build a model to identify those high-value customers with a high propensity to churn.
This session described how Tesco Mobile built the churn propensity model, how predictive analytics was used proactively to define an approach to retaining high value customers, and how this has been deployed in targeted marketing campaigns.
The presentation also demonstrated how an iterative procedure was used to arrive at the modelling definition, and how this was a key to the model’s success. It also shared practical tips and tricks based on the project.
Tesco Mobile’s predictive model delivered the capability to apply retention strategies towards customers with a high propensity to churn, and to vary the strategies according to the customer’s value. The intelligent application of predictive modelling has helped Tesco Mobile to control churn and enhance the returns from its retention programmes.
Back
|
|
PredictiveMarketing
How a creative approach to data leads to a better customer contact strategy
Frank van der Spek
Information Manager
AD NieuwsMedia BV
The Netherlands
Didier Nieuwenhuis
Client Value Consultant
Client Value Lab
The Netherlands
Netherlands’ second largest national newspaper, with a daily readership of more than 1,6 million people, uses SPSS to provide better services to its customers and to identify target groups more effectively.
This outlined how analytics enables AD NieuwsMedia to sell additional subscriptions to specific groups within its existing customer base by approaching them with a targeted proposal at the right time and through the correct channel.
A creative approach to using a customer database creates a better contact strategy, and developing an analytical and operational environment puts this strategy into operation. For AD NieuwsMedia, this led to a 23 percent saving on its first telemarketing campaign after implementing analytics.
Back
|
SPSS Predictive Enterprise Services
Deploying analytics: combining predictive models, business rules, and optimisation techniques
Sarah Dunworth
Product Marketing Manager
SPSS Inc.
UK
Predictive models, business rules, and optimisation techniques can be used within marketing departments to drive better targeting of both inbound and outbound campaigns, and within insurance claims handling departments to target fraudulent activity.
This session also addressed how to deploy models in an operational environment, including considerations such as automating the model evaluation and refresh processes to ensure the most accurate results.
Back
|
|
Dimensions
Beyond print: defining a new audience in the Internet age
Rachel Cassidy
Senior Insight Executive
Jo Green
Insight Executive
Associated Newspapers Ltd
UK
The fall in newspaper circulation and the growth of online news platforms present both challenges and opportunities to traditional print brands. In this session, Associated Newspapers Ltd (ANL) described how it is responding by using analytics to define a key segment of readers – the MidBritons.
These super-consumers are Britain’s economic engine room, with the power to make or break brands. The presentation explained how Associated Newspapers’ Strategic Insight team, in conjunction with BMRB – one of the UK’s leading market research agencies –developed a method to bring the MidBritons to life and ensure that the company is constantly up to date with the segment’s attitudes and behaviours.
ANL are going beyond structured surveys by combining sources such as online panels with blogs, scrapbooks and shared photos to deliver insights into a genuine community. ANL also talked about research that is changing the way one of the UK’s largest media organisations understands and sells to its audience, and delivers strategic feedback to the business.
Back
|
Clementine, PredictiveMarketing
Promoting the third generation: optimising telco campaigns with analytics
Silvia Codogno
Marketing CB Manager
3 Italia
Enrico Cosio
Senior Manager
Deloitte Consulting
Italy
With more than eight million customers, 3 Italia is the most important UMTS mobile phone operator in Italy. The company carries out more than 30 up- and/or cross-sell campaigns each month, and has now invested in predictive analytics to improve its marketing performance.
3 Italia adopted a two-step approach, first introducing predictive models to achieve better targeting for single campaigns, and then using SPSS PredictiveMarketing to optimise campaigns to improve contact rates, maximise redemption rates and reduce ‘noise’.
Back
|
|
SPSS Server, Clementine
Campaign prioritisation at Commerzbank AG
Heiko Güthenke
Head of Customer and Business Analysis
Commerzbank AG
Germany
Commerzbank AG runs more than 350 campaigns per year on a customer base of more than four million retail customers. In the current market environment, this results in the same customers being targeted by campaigns featuring different products. Commerzbank has tackled this problem by introducing a new analytical process called ‘Cross-Product Campaign Optimisation’.
This session was about Cross Campaign Prioritisation – from the basics to a full scale analytical approach to tackling this problem – and the technical and organisational prerequisites for optimally exploiting and leveraging existing potentials. The session also outlined an approach towards using a campaign environment for long‑term business planning.
Back
|
Clementine
How to talk to your boss about data mining
Richard Hren, PhD
Director, Product Marketing
SPSS Inc.
USA
Many organisations fail to use the power of predictive analytics to its full extent. Often, this is due to senior managements’ lack of understanding of the real value of predictive technologies.
This session discussed the best ways to communicate the benefits and value of predictive analytics to senior management and other potential consumers of analysis within your organisations.
By demystifying data mining, practitioners of predictive analytics can:
- Become advocates for predictive analytics
- Become better able to convey the results of analytic work
- Extend the analytic footprint within their organisations
- Increase the likelihood of expanded investment in their teams
- Make more powerful impact on their organisations’ effectiveness.
By driving the increased use of data in your company’s decision-making processes, people can influence the effectiveness and efficiency of multiple decision points and deliver the return on investment that is expected from analytical deployment.
Back
|
|
SPSS, SPSS Server, Clementine, SPSS Predictive Enterprise Services
Churn prediction and targeted offers in a highly competitive market
Nebahat Dönmez
Head of Customer Insights
Vodafone Netherlands
The Netherlands
The Netherlands is a highly saturated telecommunications market where there is a great deal of competition, including many mobile virtual network operators. In such an environment, post-pay customers can easily change providers at any time, and the decision is usually based on the handset without consideration for the brand.
As one of the main providers in this market, Vodafone Netherlands faces a number of challenges:
- To identify the subscribers with a propensity to churn
- To understand the reasons for churn
- To decrease the churn rate by developing targeted retention activities while controlling the retention budget with tailor-made handset or other (non-handset) offers.
Those attending this session learnt how Vodafone Netherlands’ Customer Insights Department uses SPSS technology to produce eight different monthly churn scores for two different post-pay value segments, and how, with these models, churn decreased from between 10 to 25 percent.
This presentation also addressed the approach the company took to building the predictive models, including a definition of churn and the collection and derivation of more than 2.000 variables. It also discussed the use of models within the ‘big picture’ by focusing on the example of a specific Christmas campaign.
Back
|
SPSS, SPSS Server, Clementine
Torturing your data: an analytical CRM success story
Andreas Kokkinos
Head Business Intelligence
Marfin Laiki Bank
Cyprus
Marfin Laiki Bank (Laiki) is the second largest bank on the island of Cyprus, and is growing rapidly throughout parts of Europe and Australia. However, rapid expansion in other countries caused the bank to lose focus on its core business in Cyprus, resulting in a slowdown in the growth of market share for credit cards.
After identifying the problem, Laiki launched a major effort to reach out to its customers. Using predictive analytics allied to data analysis methods, it examined areas such as churn prediction, value segmentation and campaign development.
A joint effort by the Cards, Marketing and Business Intelligence departments not only stopped the slowdown but turned it around: for the first time in its history, the bank’s rate of market share growth in credit cards is significantly higher than that of the market as a whole.
The session explained how this success was due to concentrating on basic marketing and CRM, and once more becoming familiar with the customers. It also described the processes and the functionality of the tools that were used, and how predictive analytics technology made the project much easier.
Finally, Liaki talked about the moral of its success story – “If you torture the data long enough, it will confess” – and how this approach is now being applied to all other major banking areas with quite impressive results.
Back
|
|
Clementine
Clementine 12.0 – data mining for predictive analytics
Tom Khabaza
Director of Product Marketing for Data Mining
SPSS Inc.
UK
This session was all about Clementine, SPSS’ leading data mining workbench, which delivers maximum productivity for analysts by offering a comprehensive range of capabilities, which are integrated through a visual workflow interface and support the entire data mining process.
It also covered:
- What is data mining and how does it fit with predictive analytics?
- How Clementine can be both a desktop tool and the core of a Predictive Enterprise
- New features in Clementine 12.0
- A look-ahead to the direction of future Clementine development.
Back
|
|