I don’t know about your conclusion but how you arrived at it is flawed

It has become common place in the tech and other marketing blogs – popular bloggers  making bold predictions about the future of a firm or about a technology. They state it with utmost confidence without any uncertainty. All black and white, no room for gray areas.

They back it up with scant evidence which is mostly selectively chosen to support their preconceived notion. Or these evidences are anecdotal or manufactured based on their own biased reading of the market. They fail to seek any evidence to the contrary or refuse to ask questions on what evidence will disprove their theory.

On top of this poor evidence seeking behavior we see even poorer analysis. All set up to support their foregone conclusion.

The latest in that mold comes a blog post that boldly proclaims how an enterprise software business that

  • hauls in $35 billion in revenue
  • has $29 billion in cash
  • has almost limitless borrowing power
  • has a market capitalization of $142 billion

is really doomed.

So writes Sarah Lacy in her blog.

I am not going to argue with the conclusion. I do not know what the future holds. But let us raise some questions on her  analysis (if we can call that):

  1. What does doomed mean? $35 billion in revenue wiped out? Cut in half?
  2. What are the assumptions and preconditions for this outcome? Remember, a model is only as good as its assumptions.
  3. What time frame are we talking? 5 years? 10 years? 20 years? Did she consider how long will it take to lose any portion of the $35 billion revenue or any of the $29 billion cash? What other technology and market shifts could happen during that period?
  4. One way to make a prediction is to run a scenario analysis and state in what percentage of the scenarios (and under what conditions) a particular outcome is possible. An example of such an analysis is the one by Jeremy Siegel when he predicted Dow will hit 15000. Has she run through such an analysis? What are the alternative scenarios and how likely are they?
  5. Let us consider a case where the revenue drops by 10%. Will the decision makers stand still and let the slide continue all the down to 50% and finally to 0?
  6. How many millenials will go on to install what she calls as skunkworks implementations? And if they do, will the business in question standstill and not use their cash pile and borrowing power to buyout these smaller solution providers?
  7. The story  is titled,   “$142 billion market cap business is really doomed”, backed by anecdotes quoted from selective memory and adorned with flashy narratives sounds plausible, but is it probable?

If the analysis is flawed or if the analysis is just a figment of one’s imagination, if you and I cannot reproduce the same results with the data set (in this case there is no data set) we have to reject the conclusion regardless of how plausible it sounds or how popular the blogger is.

Taking the easy option

One way to price your digital content is to give it away, for free. After all the marginal cost is $0 and there are competitors who are willing to give away for $0 what you are trying to monetize. Since information wants to be free, do not try to control it, give it away and try to monetize something else. If you are switching your offering from traditional media like print to digital, some describe you as out of touch and irrelevant trying to charge for digital content. This is the Free argument  and it is wrong. It is based on costs and competitor and completely ignores  customers  and their value.

The right marketing strategy approach is to understand your customers, the different segments and the relative utilities of different components of your offering, differentiate your offering from those who are willing to give it away and price your offering based on the value created. The problem is this is  hard, it requires truly differentiated offering to begin with and then considerable marketing research, customer conversations, plenty of data collection and analysis. There are no ready answers, no complete data and the models you build come with confidence intervals and uncertainties.

Compared to this trouble, popular fads that give simple and confident answers like “give it way” do seem attractive.

Every problem does have a  simple, attractive, confidently stated, comforting and wrong solution.