Cheat Sheet

Customer Analytics For Dummies Cheat Sheet

From Customer Analytics For Dummies

By Jeff Sauro

Customer analytics is different than many business metrics you’re probably familiar with: It focuses on customers’ needs rather than on the company’s needs. Through customer analytics, you can understand what drives customer satisfaction, customer loyalty, and repeat purchases. You’ll also understand how your customers differ or are the same and how that may affect different pricing strategies, features, and marketing campaigns.

Decide What Customer Data to Collect

It’s a good idea to understand the problems and opportunities for your customers. Collect data that falls into each of these categories to get a wide range of useful data when you apply customer analytics:

  • Descriptive: Descriptive data includes demographic data such as gender, age, geography, and income. It also includes self-described attitudes and preferences toward products, categories, and technology. You can collect this data from purchases, registrations, surveys, interviews, and contextual inquiries.

  • Behavioral: Behavioral data is the general pattern customers exhibit when using your products and services. It includes making purchases, registering, browsing, and using various devices for those actions.

  • Interaction: The interaction data includes the clicks, navigation paths, and browsing activities customers take on websites and software.

  • Attitudinal: Preference data, opinions, desirability, branding, and sentiments are usually captured in surveys, usability tests, and customer interviews.

Use the Right Methods for Your Customer Analytics

Collecting the wrong data for what you want to accomplish with your customer analytics project does you no good. Here are ten methods you can use for specific purposes:

  • Voice of customer study: This gives you a way to obtain the basic demographics of the people who purchase, make repeat purchases, and recommend your company and products to friends.

  • Customer segmentation: Segmenting customers by demographics, behaviors, and profitability gives you better ideas on how to better serve current customer demographics. It also enables you to discover any unmet needs and deliver better products and services in the future.

  • Persona development: A persona embodies the key characteristics of a customer segment by highlighting salient demographics, goals, and top tasks for development teams. Personas represent fictional customers but should be based on real data obtained from customer segmentation analyses, ethnographic research, surveys, and interviews.

  • Journey mapping: A customer journey map helps identify problem areas customers encounter while engaging a product or service and can locate opportunities for improvement. It can also help unify often disparate and competing efforts within the same organization by providing different departments with a single document that maps the customer’s entire experience with a product, service, or company.

  • Top-task analysis: A top-task analysis helps separate the critical few tasks from the trivial many by having customers pick their most essential tasks. Targeting your efforts on significant tasks and delivering a solid experience where it has the biggest impact means more satisfied customers and customers who are more willing to repeat purchase, return, and recommend to friends.

  • Usability study: You find what customers find difficult about your product or website. Observing how just a few customers use the product can uncover most of the common problems with an interface.

  • Findability study: A findability study is a specialized usability study that focuses on the taxonomy (labels and hierarchy) and ignores distractions such as the design, layout, and search capabilities.

  • Conjoint analysis: A conjoint analysis produces an accurate view of customer ratings by isolating which features have the biggest impact on preference. It’s typically used in the product development stages to understand which features to build or how changing price or options affect customers’ future behavior.

  • Key driver analysis: A key driver analysis identifies which features contribute the most to customer satisfaction, customer loyalty, or any other key variable of interest. Have customers rate their satisfaction with the most important features or functional areas of an experience.

  • Gap analysis: In a gap analysis, customers rate or rank the most important features and aspects of a product or service. Then, customers rate or rank how satisfied they are with each of the features. For each feature, you find the “gap” by subtracting the average satisfaction rating from the average importance rating.

The Steps of a Customer’s Journey

A customer journey map is a visualization of the phases a customer goes through when engaging with a product or service. Apply customer analytics, start with a specific customer segment, and then work from general to specific details:

  1. Pick a persona or segment.

    With customers segmented by demographics and behavior, you have many of the important pieces of the customer journey ready.

  2. Determine the stages.

    Construct a map around a sequence of events that happen in a timeline. This is usually awareness, consideration, preference, action, and loyalty.

  3. Define the steps.

    Construct a sequence of major steps the customer takes from awareness to post-purchase. The steps are more finely grained segments to describe the sequences through the journey.

  4. Identify the touchpoints.

    List the physical or digital interaction your customers experience during their relationship life cycle with your product or service: websites, salespeople, store, TV and radio advertisements, search engine results, direct mail, email, and social media.

  5. Identify customer questions at each stage.

    Ask your target customers what questions they have about the product or service. This helps craft branding messages, opportunities for product improvements, and the metrics you should collect to determine how well you’re addressing each stage.

  6. Find the pain points.

    At each stage (awareness, consideration, preference, action, and loyalty), understand where the customer, or prospective customer, encounters barriers or friction to making a purchase or repeat purchase.

  7. Define metrics for each stage.

    Look for metrics that are already being collected in your organization or by a third party, or collect them yourself.

  8. Identify who is accountable for each stage in the journey.

    Be sure someone is accountable to each stage, and ideally, each step. Different disciplines, from product development to marketing to usability, know their domains and metrics best.

  9. Uncover opportunities.

    Look at each of the pain points as an opportunity for innovation and improvement, and not just for damage control.

  10. Periodically validate.

    Plan on revisiting your journey map to see what information has changed and what needs to be updated.

Find Sample Sizes

With customer analytics, collecting data from a sample of customers costs a lot less and takes a lot less time than measuring every customer. The level of precision you get from even a small sample is usually sufficient to make decisions from the data.

If you have a stand-alone survey or study (no comparisons), here’s the margin of error you will have for each sample size (based on a proportion of .50 and 95% confidence).

95% Margin of Error (+/-) Sample Size
24% 13
20% 21
15% 39
14% 46
13% 53
12% 63
11% 76
10% 93
9% 115
8% 147
7% 193
6% 263
5% 381
4% 597
3% 1,064
2% 2,398

If you’re conducting a comparison study (using surveys, usability studies, or findability studies), here are the sample sizes needed to be able to detect a difference (based on a proportion of .50, 90% confidence, and 80% power). The Sample Size within Subjects column represents same participants on each version, and the Sample Size between Subjects column represents different participants on each version.

Difference to Detect Sample Size within Subjects Sample Size between Subjects
50% 17 22
40% 20 34
30% 29 64
20% 50 150
12% 93 426
10% 115 614
9% 130 760
8% 148 962
7% 171 1,258
6% 202 1,714
5% 246 2,468
4% 312 3,860
3% 421 6,866
2% 640 15,452
1% 1,297 61,822

If you’re conducting an A/B test to compare conversion rates, here are the sample sizes you need to detect differences from design A to design B for differences of .1% to 50% (assumes 90% confidence and 80% power).

Difference Each Group Total Design A Conversion Rate Design B Conversion Rate
0.1% 592,905 1,185,810 5% 5.1%
0.5% 24,604 49,208 5% 5.5%
1.0% 6,428 12,856 5% 6.0%
5.0% 344 688 5% 10.0%
10.0% 112 224 5% 15.0%
20.0% 40 80 5% 25.0%
30.0% 23 46 5% 35.0%
40.0% 15 30 5% 45.0%
50.0% 11 22 5% 55.0%