Nick Baggott's CRM and Digital Marketing Blog

Who voted for who in the UK election? A great data profiling case study

As I am sure you are aware, the Conservative Party, led by Boris Johnson, won the recent UK government election comfortably. But who voted for them and where did Labour lose out? 

Traditionally, in the UK, you would expect the Conservatives to appeal to wealthier voters and Labour to the working classes, but Brexit and the appeal of the party leaders obviously had a huge impact on who voted for who. In the Times newspaper today, there was a fascinating article profiling the voters of the main parties and I thought it demonstrates perfectly the power of data analysis. Here are some of their charts: It seems class didn't have the impact that you would expect:

But age was the key differentiator as this demonstrates:

The most astounding analysis I have seen, is what the outcome would have been if only certain ages had been allowed to vote. You can see why Labour wants to lower the age range to 16:

Just to highlight the points at the bottom of this picture (it is a screen shot from my phone, so sorry it is a bit fuzzy):

• If only 18-24s voted: Lab 600, Con 0
• If only 25-49 voted: Lab 407, Con 171
• If only 50-64 voted: Con 354, Lab 215
• If only 65+ voted: Con 575, Lab 25

Finally, did the remainers all switch to Labour and Lib Dem who were campaigning for a new referendum or to leave? Actually, not as much as those parties needed:

If you ever wondered if data could tell a story and explain a complex situation more clearly, surely this is all of the evidence you need to see the power of data analytics. 

 

CHAID, is it the most under utilised marketing technique?

CHAID, less commonly known as Chi-Squared Automatic Interaction Detector can be a wonderfully powerful tool to use to help you to understand your customers. It can predict the future and help you to understand the past. So what is it and how can it be used? 

According to Wikipedia:

Chi-square automatic interaction detection (CHAID) is a decision tree technique, based on adjusted significance testing. The technique was developed in South Africa and was published in 1980 by Gordon V. Kass, who had completed a PhD thesis on this topic. CHAID can be used for prediction (in a similar fashion to regression analysis, as well as classification, and for detection of interaction between variables. 

In practice, CHAID is often used in the context of direct marketing to select groups of consumers and predict how their responses to some variables affect other variables, although other early applications were in the field of medical and psychiatric research.

Like other decision trees, CHAID's advantages are that its output is highly visual and easy to interpret.

So, what does that mean in practice? 

CHAID allows you to create groups of customers (segments) who have similar behaviour. It also allows you to understand which of the groups is most and least likely to do something. For example, I recently worked with a data analyst who built a model looking at the profile of openers v non-openers of a client's quarterly newsletter. The model divided the previous recipients into groups with the "best" group being 10x more likely to open newsletters than the "worst" group. That has allowed the client to decide whether to stop sending it to the worst groups or maybe create a different version for the under performing groups with a different message. The latter is what they have (correctly) chosen to do, as these non-responsive groups are still customers who have recently opted-in to receive the newsletter but for whatever reason are not typically opening them.

How did the project work?

• Firstly, we agreed which recent campaign we should analyse (we chose the newsletter because it was sent to the most people, giving us the largest sample size to analyse)
• Then, we asked the data team at the client to extract 2 files. One file was the people who had opened the newsletter and the other was non-openers (as this is a B2B client the total volume is low, so we chose to analyse all recipients in both groups.If we had more data, we could have taken a sample of responders and non-responders rather than the whole file)
• In the data file, we asked for every piece of information known about the clients who had been mailed (extracting every field on the database for every record). With CHAID you never know which data field will be the most predictive, so you ask for as much as you can get and let CHAID work out which variables are most useful
• These files were handed over to our data analyst, who ran the data through his SAS CHAID software. The output was a report with 3 key elements:

            - A profile report comparing responders to non-responders for every data variable that we had available to us (eg country, job role, gender etc)

            - A CHAID tree diagram showing each of the segments and for each group what % of them opened the email. Allowing us to see which was our worst                 and best groups

            - A Gains chart which ranked the best to worst segments, so that we could easily see how predictive the model was and how much more responsive                 the best group was compared to the worst group

• These 3 things demonstrated to us that the model was highly predictive and allowed the client to very quickly see (in a highly visual format) who their best groups were and to understand the types of people who were not opening the emails. 
• The next month, they tested a new angle for the least responsive groups. They did a simple A/B test where half got the same email as the best performing groups and half got a similar email with a different subject line. We are awaiting results of that trial now...

So, how could you use CHAID? In reality, as long as you have a previous activity to analyse, you can use it to predict anything such as:

• High v low value customers
• Loyal customers v those likely to switch to a competitor
• Good payers v bad payers
• Early v late adopters 
• Attendees v non-attendees at events.....

The potential list is endless.

If you'd like to know more, let me know (email me at [email protected]) and I can discuss how you could use this massively under utilised statistical model.

Due to client confidentiality, I cannot show you my client's CHAID diagram. But, just so that you can get an idea of what the output looks like, here are a couple of example pictures I found online:

https://www.sciencedirect.com/science/article/pii/S2212571X1600007X

 

And this is what a gains chart might look like (again, one I found online):

https://www.researchgate.net/figure/Gain-plot-of-the-CHAID-and-CHAID-SPT-models_fig2_260062366

 

      

My 10 Top tips for Data Driven Marketing

Data driven marketing is still the key to marketing success. That is not just my view, a recent survey conducted by econsultancy revealed that better use of data, segmentation and targeting has become even more crucial, as they ranked it as the marketing related area that has jumped highest up their priority list for 2019. In second place, it is customer intelligence and having a full customer view, which is entirely reliant on having good quality data and superior analytics skills and tools. In 4th place, we have measuring ROI, which again is dependent upon good quality data.

In my opinion, from a data point of view, here is a checklist of the top 10 priorities for Data Driven Marketing:

• Make sure you have good quality, recently cleaned, GDPR compliant data
• Have effective data capture in all touch points
• Capture behavioural data, as a priority, as well as the overt data that is captured in forms (capture what they click on, download, open etc)
• Create automated direct marketing, that contacts the customer with relevant content, as their behaviour changes
• Build segmentation models that are simple to execute, using data that you can collect easily 
• Test and learn constantly, be agile and adapt as results come in
• Measure engagement as well as sales funnel and ROI
• Map out customer journeys from cold prospect to engaged customer, and plan out what data will be captured and how the experience will be personalised at each stage
• Don't forget to nurture cold leads who don't have an immediate interest in buying right now
• Dont just count how many people respond, profile responders versus non-responders and use analytics techniques like CHAID to build predictive models based on your results

 

Lack of testing and personalisation is common in email marketing

Dave Chaffey of Smart Insights has published a report on email marketing. The results were quite shocking to me, as I have been championing the need to personalise and test email marketing for years. That is email marketing's greatest asset and it seems that the message has not got through. Firstly, this graph shows how many marketers are simply pushing out the same emails to all customers and prospects:

And this data shows that marketers are simply not testing and learning:

If you do nothing else in email marketing, do some simple segmentation e.g. customers v prospects, or male v female, or event attendees v non-event attendees and test to see whether this works best than pushing the same message to all. Divide your audience into 3 groups:

• Test group 1 (e.g. event attendees)
• Test group 2 (e.g. non-event attendees)
• Control group (a mixture of attendees and non-attendees)

Send the generic non-personalised email to the control group and compare open rates and click through rates to the personalised messages that you send to the 2 test groups. It really is that simple!

 

Web 3.0 is coming. Personalisation is Marketers key focus in 2016

The excellent eConsultancy / Adobe Digital Trends for 2016 report is out. 

The key chart for me is this one. It shows how the marketers surveyed from B2B and B2C around the world, said that their most important priority for 2016 is personalisation. The personalised web or semantic web is already here for many brands (Google, Facebook, Amazon etc) and it looks like this has become a key priority for the majority of marketers going forward. Expect to see more behavioural segmentation, covert data capture and implementation of CRM tools as a result:

New Google Trends

Google trends has been updated. My thanks to Dave Chaffey (@DaveChaffey) for bringing it to my attention in his recent blog post. It contains a great new trending stories home page.

This example from this morning shows the impact of the shootings in Charleston on searches for Gun Control and Gun Shops. 

It also demonstrates another feature, which is the ability to see the impact on search results in real time over very short time periods. You should check it out for yourself, by searching for Google trends or just clicking on this link: New Google Trends.

In my opinion, the new features are an excellent addition to the already very useful free tool. The ability to search in such short time scales should allow brands to see the impact on their live marketing activity, whether that be a customer event in B2B or a new TV campaign, or a new product launch. 

 

 

Recent Interview with DATA2CRM blog

I have just done an interview with Data2CRM blog. I will post a link when they publish it. 

I always like to give my readers information first, so below is a paraphrased version of their questions and my answers...

1. Nick, you have a well-deserved reputation of a skilled CRM expert, as well as a proficient digital and customer-focused marketing master. What attracts you to consulting and training? I love what I do! I really enjoy the satisfaction of seeing people learn and develop skills. I also love the feedback that you get when a client tells you that they have executed your plan and it has worked. The digital  and CRM worlds are evolving and merging and it is a great challenge to keep up to speed with new developments and ideas. I am intellectually curious. I guess that means I ask lots of questions and like to learn new things and then help clients to use them to help them achieve their business objectives. 
2. CRM has opened the door for businesses of any size and industry, and delivered a new way of establishing customer relationships.  What are the essential touch points in a strategy? I agree. The technology has become more affordable and simple to use. However, that is dangerous. The secret of successful CRM is not about technology, it is about having a clearly defined customer driven strategy. Technology is only the enabler. Set objectives for customer engagement as well as revenue, and measure both. Make sure you have a true insight into why customers are behaving as they are, before you develop your strategy. So, as you save money on using more affordable technology, invest in research and data analysis.
   
   3. Due to the amount of data that you need to proceed, many companies fall by the wayside. In your opinion, what types of reports will enhance the analysis? Are there any tips to facilitate the aligning of records from various channels? Data is so accessible now. Digital channels provide you with so much information that it can be overwhelming. I always try to get clients focused on capturing behavioural rather than demographic data. Behavioural data is more accurate, robust and predictive. Can you track what behaviours a customer typically does before they buy or churn. For example, if you are a mobile telco, if a customer rings a competitor just before their contract runs out, it tells you that they are looking to switch. Segment and communicate using behavioural data and you won’t go far wrong.
   
   4. Customer segmentation is vital for sales and marketing performance. What is the difference between B2B and B2C strategies? Can manufacturing and financial companies apply the same approaches? B2B marketing often focuses more on thought leadership, whereas consumer marketing is more about brand and customer experience. I typically advise B2B customers to focus on developing engaging and educational thought leadership content, using channels like blogging and YouTube. When a customer is ready to start their long buying cycle in B2B, they will research first online before they contact you. Make sure that when they start hunting for information, then your content is what they find on Google or in their industry forums.
   
   5. Social media is a new channel for building company brands. Nick, what are the key stages of planning this strategy?  Social media is here to stay. Google say that marketers should look at the world through a digital lens as that is what consumers do. Eric Qualman said, “Social and mobile are not emerging, they are merging”. Think mobile and social in everything that you do, whether you are B2B or B2C. To plan a social strategy, focus on the 4 stages of customer engagement. I call these acquire, participate, engage and share. This means – get their attention, get them to respond, develop an ongoing dialogue and then make it easy for them to become advocates and share your content with your peers.
   
   6. Customer retention and loyalty depend on the convenience and relevance of the service. Does the process of lead generation require only online engagement? How can companies increase their customer acquisition? Customer acquisition is about having content that people want to share and will find when they are searching. The days of mass “push” style outbound marketing are numbered. Rather than focusing on sending your message out to everyone and hoping that a few people respond, focus on inbound “pull” marketing. That means when they are ready to buy, they will find you. Digital channels are great value as you only pay when the customer clicks through to your site. Google search, social media ads and display advertising are effective as they can be targeted based on customer behaviours.
   
   7. The effectiveness of a CRM solution has a direct ratio to the level of user adoption. Can companies, which spare on employee training, achieve an immediate ROI from their CRM initiative? Would you mind to offer few pieces of advice on improving the end-user adoption? CRM tools are now simpler to use as well as lower cost. In the past, businesses had to adapt their business model to match the software. Now the software adapts to the way that you work. A good CRM consultant will help you through the process. However, getting results is not about using the software effectively it is about having a clear customer focused business strategy. Businesses need to invest in training their staff in understanding customers, generating insights and using digital inbound channels more effectively as well as user training to help them to adopt the software package. People will invest time to learn how to use the software if they can see that the business is getting results. For example, a sales manager will be more inclined to input their data and use the software if they are getting higher quality leads that convert. It is all about the CRM and digital communications strategy

Here is the link: http://www.data2crm.com/migration/blog/interview-with-nick-baggott-the-secret-of-successful-crm-is-not-about-technology/

 

CIM Hackathon 2025

I've just contributed an article to the CIM Marketing 2025 Hackathon debate. I have written about the links between big data, social CRM and social media. Please read, comment and share. Anyone can set up a profile and contribute articles under 8 marketing topics, based around what marketing will be like in 2025. PLease check it out! 

How to improve the effectiveness of your data capture forms - infographic

Lisa Margetis of Single Hop sent me this neat infographic, based on some research that her company has done. It talks about the importance of not asking too much. Make sure you just keep to the key information. You can always collect more in future interactions, but there won't be any future contacts if you make the form too complex.....

 

Email usage report - retention not acquisition focus

The DMA have recently published a trend report on marketers use of email. It is called The National Email Benchmarking Report. You have to be a member to access all of the data, however some interesting stats are highlighted in the summary on their web page:

- Emails hit all all time high in November 2012

- Volume of emails were up by 25% in H2 2012 when compared to the first half of that year

- The primary reason for using email was "ROI" an encouraging sign (previously the most common use of email was for seasonal activity)

James Bunting, Chair of the DMA Email Marketing Council’s benchmarking hub said:

“It’s no surprise to me that the number-one factor driving up email volumes is 'effectiveness/ROI is playing a greater role'. Triggered and automated emails have diminished the reliance on seasonality as a key factor for volume, and with the expansion of technology in this area I can only see that trend continuing to raise frequency and ultimately volume. This is all great news for our channel proving that email still delivers ahead of some of the more fashionable channels.”

Other interesting findings include:

- List volumes have increased by 36% over the year, showing a growth in data capture for CRM

- A focus on retention rather than acquisition as the key reason for using email, again showing the importance of email to CRM programmes.

Source: IDM Insight Bulletin from DMA Report data