"Churn"

GROWTH HACKING
How To Fight Churn: An AI Approach


Why is there so much theory on conversion optimization in relation to churn prevention?… 🤨

Smart business people know that business growth isn’t just about attracting new customers. Sure, bringing in new people is exciting, and seeing the numbers grow makes you feel good, but it’s actually not the answer to profit.

Customer retention is where it’s at. Because whilst growth occurs when new customers, if two many customers leave it counteracts the growth and can even lead to contraction. Did you know that the cost of acquiring a new customer can be higher than that of retaining a customer by as much as 700%, and increasing customer retention rates by a mere 5% could increase profits by 25% to 95%?

One factor is customer lifetime value (CLV). Over a long period, one customer who comes back time and time again, always increasing their spend or adding to their basket, will be worth far more than a few customers who pop in once for the cheapest service on offer. 

Attracting customers takes a lot of effort – and therefore costs money. We’re not saying that you don’t have to put effort into looking after your existing customers, of course you do – but that effort manifests rewards many times greater.

What Is Churn?

The metric we use to measure this is churn.

It looks at how successful you have been at acquiring and retaining customers. What we classify as a ‘lost customer’ has a few nuances:

In some cases the customer actively ceases their relationship with you, such as by terminating an account. This is called absolute churn. In other cases, they don’t change their status ‘officially’ but do stop engaging with you – presumed churn.

The time period to measure by also varies. For a newspaper, a customer could be classified as lapsed after only a couple of weeks of not buying, whereas for an airline it could be many months, and a car company would be looking at years.

How the churn happens is another consideration. It’s called reactive churn when it’s something specific, such as bad customer experience causing someone to cease dealing with a business, and prospective churn when nothing specific has happened, but there’s a slow moving away from engagement.

To manage churn you need to be able to identify the triggers and address them. This is where an AI driven approach comes in.

How AI Can Help To Fight Churn1. Understanding The Relationship Between Negative Triggers And Their Effects

Using historical data, businesses can study the link between negative customer experiences and customer response, and address them. If it’s known that this trigger is likely to lead to a customer leaving, it’s important to remedy it. This can include internal triggers, such as customer engagement, and external, like price cuts, although the latter are difficult to deal with.

2. Understanding Fading Behaviors

Historical data can also be used to predict prospective or slow driven attrition. By mapping existing customers with historical customers who have fallen away, it’s possible to predict who are at risk of lapsing. They might be exhibiting behaviors such as reducing frequency of purchase, not using loyalty cards, or cutting down on engagement.

3. Identifying High Risk Clusters

Using a decision tree model allows to segment the customer population into clusters linked together by specific behavioral characteristics. It’s then possible to see which have a high churn risk.

For example, you might discover that customers who join less than a year ago and spend less than $25 a month are more likely to leave. You then know that they are high risk and can treat them appropriately.

Let’s take a look at a fictional company – a data analytics software for building and sharing real-time business dashboards that can be created and use by multiple users.

The figure here  uses a technique called Behavioral Cohorts to show the relationship between a behavior and churn.

🧐 How to read: Each pool of customers, along with a behavioral metric, gets organized into a specific cohorts depending on their measurement in that metric. Usually ten cohorts are used, so the first cohort contains the bottom 10%, the second the next 10%, and so on.

As the bottom of the behavioral cohort plots is always set to zero churn rate, so the distance of the points from the bottom of the cohort plot can be used to compare relative churn rates. So if one point is half as far from the bottom of the plot as another that means the churn rate in that cohort is one half the other.

It also reveals that the churn rate on the cohort with the lowest active monthly users per month is around 8 times greater 😲 than churn in the cohort with the highest number of active users. 

The next figure show the license utilization metric calculated by dividing the number of active users by the number of seats the user has purchased – a seat means the number of users allowed.

This shows that license utilization is a very effective metric for fighting churn: the lowest cohort in license utilization has average utilization just above zero, and the highest cohort has license utilization around 1.0, and the lowest cohort has a churn rate that is nearly seven times that of the highest cohort. This makes it more effective for distinguishing churn risks than solely looking at active users.

You want to do this analysis also for your business? Get an account for RetentionX.

Beware Of The False Positives

One issue with churn management is the high prevalence of false positives in churn prediction models.

How can you determine, if a customers is just late with his next purchase or is already churned? 🤔

They have significant detrimental impact on programs, driving costs up, for no reason. Essentially, you would be spending money trying to retain customers who were never really at risk of leaving.

There are ways round this.

One step is increasing the number of data points, both in terms of types of data (e.g. enrich transactional data with customer experience data, marketing campaigns data etc.) and volume of data (e.g. number of months of data being used).

You can also exploit model heterogeneity by selecting different models that may be most effective for specific predictions (e.g., SVM, Neural Nets, RBM, Collaborative Filtering) and bringing them together to optimize overall performance.

What Data Is Required For Churn Management?

As is true in most cases, the more data you have, the better. Try to get a 360 degree view of every way that your customer engages with your business, giving you a fully holistic picture.

👉 Transactional data, such as spend across categories, purchase frequency and SKUs bought, as well as product attributes.

👉 Customer demographics like age, gender, lifestyle and location, and their experience with you on a loyalty program.

👉 Pricing, rates, timelines and schedules, and engagement with you through services and history.

👉 Marketing, campaigns and offers and how they responded.

👉 Macroeconomic factors such as interest rates, unemployment rates, economic growth, and seasonal effects.

The All-Important Question Of ROI

Of course, it is not enough to just identify the customers that are at a high risk of churning. You have to do something about it, and make it worthwhile.

The investment in addressing the attrition risk at an individual customer level has to reap rewards. AI and machine learning can help here, and offer three key steps to treat likely churners in the most effective way.

👍 Determine Customer Attractiveness: Not all customers are equal. The first thing you have to do is work out how important – which usual means how valuable in dollars – each individual customer is to you so you can spend your money on those who have the highest lifetime value for you. Modeling can use spend, revenue, wallet size, basket size, frequency and other patterns to be used to define attractiveness.

👍 Identify Customers’ Sensitivity To Treatment Inventory: Next it is important determine what are the most effective treatment strategies for each customer. You need to consider the type of campaign or intervention they would best respond to, and the types of communication channels that are most effective in each individual situation.

👍 Test And Learn Feedback Loop: Even knowing which customers you want to go after and which strategies might work best, you still need to be testing and learning. It’s important to be able to respond quickly, and learn from the strategies you place and the responses they gain. A nimble and agile organization can continually learn and hone their strategies using a fast feedback loop.

None of this is easy to do, but it is important. Thankfully there is software out there that does the job.

Pioneering market leader RetentionX translates your data into clear actions. By using AI-driven data analysis in an easy to use tool, it allows you to make business changing decisions driven by effective machine learning. As the most sophisticated data science engine out there it uses modeling, machine learning, and artificial intelligence to analyze data, allow you to benchmark stats, and deliver insights that you can act on.

My hometown in the 50s and 60s

Just some pictures I happened upon.

Regicide

With walls of amiability established,
and fortified in resilient reciprocity,
no one shall see the pejorative consumption, inside;
not even when those walls, one day, disappear.

Been a while and had nothing better to do.

Coulda Shoulda

I could have had a fishy,
except the cat's paw is always swishy.

I could have had a lion,
although I'd just be a cryin'.

I could have learned falconry,
but instead, I ate a bowl of macaroni.

I could have just learned to fly,
so that I could just soar, and watch it all go by.

I should have had a muse,
or rather, one that I didn't confuse.

I should have had a mentor,
imbued with that special form of candor.

I should have learned to just take more time,
much simpler and so tranquil; it would have been just fine.

blehh

Friday, March 11
The National Commission on the Deepwater Horizon Oil Spill and Offshore Drilling (an independent entity created by President Obama on May 22, 2010, to investigate the disaster) ceases operations. The investigation concluded that the oil well blowout was preventable and "can be traced to a series of identifiable mistakes made by BP, Halliburton, and Transocean that reveal such systematic failures in risk management that they place in doubt the safety culture of the entire industry."

Read more: Infoplease.com http://www.infoplease.com/world/disasters/2010-gulf-oil-spill-timeline.html#ixzz1K52Mt0jw

Knowing that people over 2,000 years ago already understood this --

-- before their views were declared heresy by Christians and destroyed.

"[T]he world was produced by the working of nature, without there having been any need for a process of manufacture, and that what your school declares to be capable of accomplishment only by means of divine intelligence is a thing so easy that nature will produce, and is producing, and has produced worlds without end. It is because you do not see how nature can accomplish this without the help of some kind of mind that, like the tragic poets, in your inability to bring the plot to a smooth conclusion, you have recourse to a god. Yet you would certainly feel no need for his agency if you had before your eyes the expanse of region, unmeasured and on every side unbounded, upon which the mind may fasten and concentrate itself, and where it may wander far and wide without seeing any farthermost limit upon which to be able to rest. Now in this immensity of length and breadth and height there floats an infinite quantity of innumerable atoms which, in spite of the intervening void, nevertheless join together, and through one seizing upon one, and another upon another, form themselves into connected wholes, by which means are produced those forms and outlines of the material world which your school is of opinion cannot be produced without bellows and anvils. You have therefore placed our necks beneath the yoke of a perpetual tyrant, of whom we are to go in fear by day and night, for who would not fear a god who foresaw everything, considered everything, noted everything, and looked upon himself as concerned in everything,—a busy and prying god? From this has come, in the first place, your idea of preordained necessity, which you call ε μαρμένη, meaning by the term that every event that occurs had its origin in eternal truth and the chain of causation—(though what is to be thought of a philosophy that holds the ignorant old crone’s belief that everything happens by destiny?)—and secondly your art of μαντικ , or divinatio, as it is called in Latin, which, if we were willing to listen to you, would imbue us with such superstition that we should have to pay regard to soothsayers, augurs, diviners, prophets, and interpreters of dreams. From these terrors we have been released by Epicurus, and claimed for freedom; we do not fear beings of whom we understand that they neither create trouble for themselves, nor seek it for others, and we worship, in piety and holiness, a sublime and exalted nature."
- The Nature of the Gods; Cicero, 45 BCE

MacGyver is a "good" counterpart of James Bond

"Back in the 1950s, James Bond was selected as the ideal super soldier specimen to be cloned. However, as Metal Gear Solid has proven, only a genetically perfect clone can exhibit such radical differences. Observe:

* James Bond is a cool name. Angus MacGyver... isn't.
* James Bond is sexy and dangerous. MacGyver is the type of boy that your father would set you up on a blind date with.
* James Bond wears expensive designer suits. MacGyver wears a suede jacket with a polo shirt and blue jeans (or cargo pants).
* James Bond drives the coolest cars from Aston Martin, BMW, and Lotus. MacGyver drives a dingy old Jeep, which (to avoid risking coolness) is later replaced by an old station wagon.
* James Bond is supplied high tech-gadgetry by Q Branch that run on nonsensoleum. MacGyver builds his own gadgets from mundane objects (although he also has a pocket Infinite Improbability Drive that he uses on them).
* James Bond has no problem with killing people and legal permission to do it. MacGyver tries to avoid killing people; his villains die (when they die) by accident or by direct application of the Villain's Gambit. James Bond uses guns while MacGyver doesn't.
* The number of women James Bond has chosen not to sleep with is exactly the same as the number of women that MacGyver has slept with (i.e. very few).
* James Bond, in spite of never seeming to use any contraceptives, has never ended up with children from any of the women that he has slept with. MacGyver, however, manages to end up with one in spite of the very few women he has slept with and the fact that one would assume he would use contraceptives.
o Even if MacGyver didn't have any contraceptives, he would probably be able to make one out of like, a rubber band and a condom or something.
o Or maybe, just, you know, use the condom. Unless the rubber band is for extra added springyness, maybe?
o Maybe the condom was a magnum and he needed an elastic waistband at the bottom? Because he couldn't "fill it out"?
* James Bond saves the world. MacGyver saves the kids of the community from counterfeit baseball cards.
* James Bond spends Christmas saving the world from a bioterrorist threat. MacGyver spends Christmas helping a local gym run a charity play.
* James Bond spends his free time in casinos, gambling with high stakes and scoring with plenty of beautiful women. MacGyver spends his free time going on nature hikes and doing social work with the community.
* On the flip side, James Bond enjoys golf, a sport second only to shuffleboard amongst old retired men. MacGyver enjoys hockey, a sport second only to rugby for brutal violence outside the rules.
* James Bond managed to kill his archnemesis eventually. MacGyver's unwillingness to kill anybody is so powerful, it selectively rewrites the laws of the universe to allow Murdoc to survive crumbling buildings, point blank explosions, thousand foot falls, and being submerged in boiling water.

Unfortunately, MacGyver just wasn't good enough for British Intelligence; he was missing that essential bull-in-the-china-shop quality. So he was traded to the United States. The rest is history.



- MacGyver has three brothers; their names are Alton Brown, Adam Savage and Jamie Hyneman.

There is no better explanation.



- MacGyver is a Spark

He can improvise complex devices out of any available material, and they always work even when physics says they shouldn't.



- MacGyver is a near-immortal being who engenders the Starfleet Corps of Engineering.



- In NextGeneration episode The Survivors, we learn that one Kevin Uxbridge is a Douwd: an immortal, Q-like race that specializes in hiding their identities. However, we have seen Kevin Uxbridge before: Harry Jackson, Mac's grandfather. Jackson cared for Mac after his "real" parents were killed; eventually they were estranged and later reunited. We know that the Douwd specialize in false identities AND that they can love humans. Since they are nearly omnipotent, it is conceivable that they would be able to foster children with humans. Therefore, we can postulate that Uxbridge, living on Earth, impregnates Mac's mother and then creates a "false father" in his own image (we have seen Uxbridge do something similar), possibly so that Mac will grow up with two human parents. After their deaths, Uxbridge regrets his decision and isolates himself from his progeny to protect Mac from finding out he's half-Douwd. Mac's half-Douwd nature gives him long life and subconsciously powers his physics-defying prowess: either he bends physical law to conform to his needs, or creates useful items in proximity to himself when in danger. His constant manipulations of reality give rise to weird phenomena that span the universe, creating subspace and other Star Trek phenomena, as well as explaining all the physics-defying moments in the series. Uxbridge, who indulges often in denial on a massive scale (as we see in The Survivors), only eventually accepts that he is directly responsible for Mac's actions and, after a brief period of reunion to ensure Mac has developed in a sensible direction, fakes his own death so that he can relocate and start another new life. The Starfleet Engineering connection is now obvious. That branch of Starfleet produces miracle workers on an absolutely unheard-of scale, with their own physics-defying aura and problem-solving ingenuity. The "main cast" engineers (all human or partially-human, mind you) must all either have studied at the feet of the master, or must be his descendants. Their own short-lived nature comes from the dilution of Douwd blood.

* Transporter Chief O'Brien was also contemporaneous with Mac, but since the episode in which O'Brien and Mac interact featured time travel, it's likely this was just a time travel accident."

I found this @ http://tvtropes.org/pmwiki/pmwiki.php/WMG/MacGyver

The true burden we face today, is not in the systems we create to move us forward, but in the citizens we aren't creating that hold us back. - Me

Just wanted to make it clear who said it that way first.

.. because he had a dream.

Some outstanding quotes by MLK Jr.

History will have to record that the greatest tragedy of this period of social transition was not the strident clamor of the bad people, but the appalling silence of the good people.

He who passively accepts evil is as much involved in it as he who helps to perpetrate it. He who accepts evil without protesting against it is really cooperating with it.

Faith is taking the first step even when you don't see the whole staircase.

We may have all come on different ships, but we're in the same boat now.

The means by which we live have outdistanced the ends for which we live. Our scientific power has outrun our spiritual power. We have guided missiles and misguided men.

I refuse to accept the view that mankind is so tragically bound to the starless midnight of racism and war that the bright daybreak of peace and brotherhood can never become a reality. I believe that unarmed truth and unconditional love will have the final word.

Darkness cannot drive out darkness; only light can do that. Hate cannot drive out hate; only love can do that.

We must accept finite disappointment, but never lose infinite hope.

Everything that we see is a shadow cast by that which we do not see.

The moral arc of the universe bends at the elbow of justice.

A nation or civilization that continues to produce soft-minded men purchases its own spiritual death on the installment plan.

The question is not whether we will be extremists, but what kind of extremists we will be... The nation and the world are in dire need of creative extremists.

Almost always, the creative dedicated minority has made the world better.

We must build dikes of courage to hold back the flood of fear.

Discrimination is a hell-hound that gnaws at Negroes in every waking moment of their lives to remind them that the lie of their inferiority is accepted as truth in the society dominating them.

Our lives begin to end the day we become silent about things that matter.

When you are right you cannot be too radical; when you are wrong, you cannot be too conservative.

There can be no deep disappointment where there is not deep love.

Philanthropy is commendable, but it must not cause the philanthropist to overlook the circumstances of economic injustice which make philanthropy necessary.

Rarely do we find men who willingly engage in hard, solid thinking. There is an almost universal quest for easy answers and half-baked solutions. Nothing pains some people more than having to think.

Shallow understanding from people of good will is more frustrating than absolute misunderstanding from people of ill will.

The art of acceptance is the art of making someone who has just done you a small favor wish that he might have done you a greater one.

We must concentrate not merely on the negative expulsion of war but the positive affirmation of peace.

The limitation of riots, moral questions aside, is that they cannot win and their participants know it. Hence, rioting is not revolutionary but reactionary because it invites defeat. It involves an emotional catharsis, but it must be followed by a sense of futility.

We must develop and maintain the capacity to forgive. He who is devoid of the power to forgive is devoid of the power to love. There is some good in the worst of us and some evil in the best of us. When we discover this, we are less prone to hate our enemies.

We all must learn to live together as brothers or perish together as fools.

-- Just a snid-bit of wise words from a single voice; on this the day of his remembrance.

Oktoberfest in Leavenworth featuring my Great Aunt Jo and Cousin Kyle.

http://sigabnw.blogspot.com/

My cousin works with a radio station there.