Tag Archives: analytics

Startup metrics – one VC’s top 10

Posted on by
Reply

Here’s Redpoint VC Tomasz Tunguz’s top 10 metrics, including a new one for me – TSM – or trailing six month (average), which he says are the ones he’s found most useful in board meetings:

With the analytics tools today, it’s easy to measure hundreds if not thousands of different metrics for your business. Cutting through all the chaff to determine the most important or insightful metrics can be quite a challenge.

Below are the ten metrics I’ve found to be most useful in board meetings. They answer the questions of how should a startup founder might measuring the business at the highest level. You should have many more metrics than these, but I’ve highlighted the ones that I recommend presenting to your board and reviewing each week.

Metrics Format

Clear data leads to productive conversations. To best understand a data point and its implications, we have to put it in context.

I’ve found dividing top level data in three slides, one for company priority (Distribution, Engagement, Revenue) helps to set the right context. Within the slide, a table that shows the metric and compares it to last month, then explicitly calculates the monthly change, the trailing six month average and finally compares the metric to the goal best communicates the state of that metric. See below for an example.

Metric This month Last Month % change TSM Average Goal
Active Users 100,000 50,000 100% 125% 75%
Total User Base 500,000 400,000 25% 7% 10%

The TSM Average column is the Trailing Six Month Compound Growth Rate. It is calculated in this way:

(ending_value/starting_value)^(1/num_periods-1)-1.

In most businesses, a monthly growth percent is too volatile to be meaningful. However the TSM Average smooths out the monthly change. Comparing the monthly to the TSM, we can get a sense of whether the monthly growth is accelerating or decelerating and how it compares to the goal you set each quarter. In this example, the total user growth was slower this month than in the past six month, but activity is way up. The next question, the one board members and founders should ask, is why?

Metrics/Question Pairs

Now that we have the base format of the metrics, let’s talk about which metrics matter. Each metric is followed by the question it’s designed to answer. Pick the ones that are relevant to your business.

Distribution

  • New users added last month by channel/TSM growth rate: How are well are we growing the user base? Which user sources are the best?
  • Total user base/TSM growth rate: How important is our monthly growth compared to our total user base?
  • Cost of customer acquisition, lifetime value, pay back period: Can we grow faster through paid acquisition? Are we acquiring customers profitably? How much can we afford to spend on new customers? How is this changing over time?

Engagement

  • Active users (can defined in several different ways depending on your product) by channel/TSM growth rate: Are we getting better at giving our customers what they want/need? Which channels of users are most effective in finding us the right kind of user?
  • % of users using top 3 key features in a given month: Are our product initiatives the right ones?

Revenue

  • Revenue / TSM Revenue growth: Are we growing our revenue?
  • Conversion to paid rate in that month/by cohort: How many users converted to paid? Are we improving our ability to convert customers to paid?
  • Avg spend per paying customer of a managed account vs solo account: What is the impact of the account management team?
  • Churn rate/ TSM Churn rate: How well do we retain our customers?
  • Burn rate: When are we profitable? When do we run out of cash? When do we need to raise?

These are the metrics that have been most valuable/insightful for me working with our companies.

So if that didn’t do the trick and get you focusing on the numbers maybe this fun video from Guy Kawasaki at UC Berkley will help – skip to 08:30 to bypass the introduction – and to get straight to the first mistake entrepreneurs make:

Guy focuses on one simple message, if you wanted to sum it up, it’s that’s VC’s are just interested in the numbers. But that begs the question, what numbers are they interested in when seeking investment?

Here’s Tomasz’s answer when I asked him that generic question: “Each business is different. Each VC is different. But ultimately if you can show profitable unit economics I think that’s a good start.”

So my suggestion? To give yourself a better chance of succeeding ask the VC before your meeting what they use as key generic KPIs to judge investment, and why? Then adapt to your specific business case.

eBay's sportscar

‘Thinslicing’ connects the data, to the behaviour that creates it

Posted on by
7

If you’re here for the two examples of companies that improved customer service by allowing people (customers) to talk to people (employees), highlighted in red – and the 2nd example is in the 3rd comment. You can ignore the stuff about thinslicing:-)

To explain why I like the term thinslicing first take a look at the cool piece about data interpretation written today by Lithium’s Dr Michael Wu, including this neat illustration:

Then consider this, that my response to reading this blog post clarified a key thing I have been trying to say. Firstly, that I’ve come to term the business objective of finding the “interpretable, relevant and novel” in data as Michael terms it – through a combination of art and science – namely that of thinslicing.

thinslicing

But now I’ve made the next step. Identifying the value of thinslicing lies in the elegant and powerful way the term thinslicing connects the approach to data analytics to the behaviour that creates that data – namely with the thinslicing of online consumers who “tend to ignore most information available and instead ‘slice off’ a few relevant information or behavioral cues that are often social to make intuitive decisions,” as Brian Solis puts it. 

But perhaps it would help if I made clear what I don’t mean by thinslicing as a strategic tool, is that summed by nicely in these two paragraphs written by Bob Thompson on the CustomerThink community:

“Despite our best efforts to collect and analyze data, good business decisions will always include elements of judgement, intuition or just plain luck. Many day-to-day decisions are made with little or no thought, because the option selected just seems “right.” Gut-feel decisions might be examples of what Malcolm Gladwell called “thin-slicing” in his provocative 2005 bestseller Blink.

“However, the best decision can sometimes be counter-intuitive. For example, the financial services firm Assurant Solutions wanted to improve its “save” rate on customers calling in to cancel their protection insurance. The industry’s conventional wisdom, which resulted in 15-16% retention rates, was to focus on reducing wait time to boost customer satisfaction. But data analysis found a solution that tripled the retention rate: matching customer service reps with customers based on rapport and affinity.”

What I mean is the approach to data as you outline above which I categorize as thinslicing, coupled with the way consumers make purchasing decisions – which like good business “will always include elements of judgment, intuition or just plain luck”.

In other words by thinslicing, rather than using intuition to make decisions, I mean adopting a strategy which is based on the understanding that by connecting the means of analyzing the data with the way the data is created by customers.

The question then is why? While it may be clever to see a way which logically connects the way to analyse data with the way it’s created, why is that potentially so useful to a business? Now there’s a good question. The obvious answer is that by aligning the analytic method used by your business, with the way the data is created by your customers, you are going to produce better results in terms of both better quality actionable recommendations which also produce an increase in ROI. How does that sound?

Update: so there’s a nice response from Dr Michael Wu on that question of linking the too together, the way you approach the data, with the way its created, that connects the two ends of the spectrum together:

Good data scientists must know everything that happen to the data, from its creation, all the way to the point where they get their hands on the data. It is actually a pretty standard practice for hardcore financial/business analysts. Not only you need to “connecting the means of analyzing the data with the way the data is created,” you must know everything that happen to the data along the way, until the data reaches you (or the analyst). Only then can you be certain that your analysis is not biased or confounded by something before you get your hands on it. In statistics term, only then can you know the confidence interval of your result.