## August 20, 2009

### OMS: Real-Time Scoring

In my OMS projects, I create three different families of scores:
1. Probability of a customer purchasing in the next twelve months.
2. Amount a purchaser will spend in the next twelve months.
3. Factor analysis scores for channel x merchandise combinations.

The scores yield a series of segments --- as few as maybe 80, as many as several thousand.

Each segment has a predicted future value --- that future value fuels the simulation of five year sales and profitability of your online business.

This information could easily be incorporated into your Web Analytics platform, allowing you in real-time or near real-time to see how today's purchasers influence the future trajectory of your business.

For example, you query customers who purchased in the twelve months ending last night. Each customer is scored via the OMS algorithm, and placed in one of the segments. Then, the future value for the next twelve months is summed across segments. At this point, you know that your current twelve-month buyer file is going to generate, say, \$33,000,000 in the next year.

Tomorrow you have an e-mail campaign that goes absolutely bonkers. Woo-hoo! Replicate the scoring process mentioned above, just shift the twelve-month window by a day, and re-score everybody. Sum future volume. Say the total is \$34,000,000. Now you know that your e-mail campaign went bonkers today, but also added a million dollars of value to your future business.

That's something you'd want to know, wouldn't you? And knowing it in real-time or near real-time is even better.

1. Kevin, might be interesting to find out the answer to the opposite question as well: if the above is *not* something you want to know, how come you don't want to know?

The universal answer I hear is "my boss doesn't care about that kind of thing". The reason the boss doesn't care is his boss doesn't care, and so forth.

Begging, why don't they care, what is the root cause? Frequent answers are:

This company is run by sales, not profits.

Even if we knew this information, there's no way for me or my boss to act on it.

I'm only going to be here a year or two, why should I care what happens next year?

There is something really unique about the kind of culture that understands the ideas you presented above and knows how to act on them. Catalog companies were basically born and raised by optimizing profit, and attract people who understand that culture. Web operations, not so much. Which leads us to:

1. What defines this culture?

2. Why should a company want to embrace this kind of culture?

3. If a company wants to embrace this kind of culture, what's the best way to go about making it happen?

2. Hi Jim, thanks for the message.

I might have to pose that question.

This OMS process is clearly cultural. The Web Analytics community is downloading the paper at record levels (compared to other things I've authored).

But that's where it stops. No tweets. Almost no re-tweets. No blog entries. No questions, no e-mail sent to me asking for more details. No criticisms (you get criticized when people understand what you are saying but disagree with it). No snarky comments. All of the interaction that happens in the catalog world with Multichannel Forensics is missing with the online community and OMS.

So, we'll just start teaching, and see where it takes us. It seems likely that your culture comments will weigh more than any profit and business intelligence that can be derived by the methodoloyg.

3. Hi Kevin,

I have read your presentation twice now, and although I come from a catalogue background, I think some of the concepts you need to unpack slowly.

I have concerns about the 'how' of the data capture exercise, I also have more queries about the analysis process itself.

I think this medium (blogs,presentation) may not be working in your favour. It could be that a video and slides might work better, or at least to complement the existing material.

I am keen to get my head around this, and I think I know where you are going with this having read your book, and hope you consider different forms of presenting this material.

On a lighter note, I found it *funny* that Duncan Berkshire went on a spectacular, but insightful, rant about the over-reliance on algorithms, and then you promote the "the power of the OMS algorithm".

Best wishes and keep pushing the online community.

Dan

4. Thanks for your comments, Dan, I'll see what I might be able to do.