Trader Talk

Solving the investor's Big Data problem

Kensho: Who benefits from gas shock?
Kensho: Who benefits from gas shock?
Leveling the playing field
Leveling the playing field
Kensho dives deep into BBY & CRM
Kensho dives deep into BBY & CRM
Pisani opens up Kensho's Stats Box
Pisani opens up Kensho's Stats Box
CNBC partners with Kensho
CNBC partners with Kensho

Did you ever hear or read a comment about a market trend and wonder how accurate it was over a certain time period? Or when some trader says, "We are entering a seasonally strong period of the year," did you ever wonder exactly how often that was true, and under what circumstances?

Sure you have. All of us who cover the markets engage in this kind of research every day.

Today, CNBC has announced a strategic partnership with Kensho, a company that was set up to answer complex financial a few seconds.

Read MoreTrader stakes millions on gold miners

That's right. A few seconds. Data mining is a key part of the life of any financial reporter, as well as hedge funds and other professional investors.

Getting a trader's edge: A brief history
Getting a trader's edge: A brief history

The problem is, it takes up a STUPID amount of time to get the answer to many simple research questions. It could take hours, and often it requires bringing in someone from the outside.

But thanks to the burgeoning field of big data analytics, it's getting easier to acquire and crunch information. And much less expensive. And that means there will be more time available to think about broader issues and to uncover relationships that may not have been obvious before.

It also means the average investor is about to get access to investment insights only the pros had access to in past.

Read MoreHow this company is 98% sure you want that parka

This is good news. Wall Street is among the last industries to embrace Big Data for the average individual. Sports business, for example, has made good use of Big Data for a couple years now (just look at the mass of statistics in an average NFL game).

Why has Wall Street been so slow to embrace Big Data for the masses? I don't know, but my guess is that it is a threat to the business model of a lot of firms.

Hedge funds, for one, rely on the fact that it is difficult to get answers to certain questions. That's how a lot of them make money! Indeed, for a many hedge funds, data mining is essentially the "secret sauce" that enables some firms to outperform others.

Kensho is the brainchild of Daniel Nadler and several ex-Google programmers. I met Dan earlier this year during a series of interviews I conducted with him as part of the Exponential Finance Conference CNBC co-produced with Singularity University. He did his doctoral research at Harvard and is now director of research for financial technology at Stanford School of Engineering.

Simply put, Kensho allows you to answer the question, "What happens to some set of assets (like the S&P 500) when some set of conditions is true?"

What happens to South African mining stocks immediately after the resolution of labor strikes? If Apple launches a new iPad, how does the stock—and the market—perform historically right after that happens? What happens to the S&P 500 on a day when the quarterly GDP report comes in well above estimates?

These are relatively simple questions, but getting a clear answer often takes up a lot of time.

Kensho makes this easy, or at least easier than it used to be. It was designed for professionals to help them understand the market from a statistical point of view. It looks at historical patterns but it can also test ideas.

Let's take a simple example: what happens to the markets when oil drops 20 percent, as it has recently? What sectors benefit?

According to Kensho, there have been 16 periods since 1999 when oil dropped 20 percent or more over a 2-month period. Not surprisingly, Consumer Discretionary stocks (retailers) responded strongly, up 0.6 percent on average in the month following the decline.

That makes sense: lower gas prices are good for consumers.

But some of the findings are counter-intuitive: the S&P on average was down 0.6 percent in the month after the 2-month decline.

Hmm. Here's another surprise: energy stocks on average were up 0.18 percent in that period. You would think energy stocks would decline as oil declines.

Why is that? Kensho doesn't answer that question, but that's what makes this fun: it forces us humans to think a little bit more about what is going on beneath the mass of market statistics. My guess is that by then, two months after oil has dropped, oil is likely rebounding from oversold levels, and so are energy stocks.

So buying at those lows during the first two months was likely a winning strategy.

That's an interesting insight, but what's more important is that using Kensho you can perform these calculations in a few minutes, including the time it took to enter the parameters.

And it's surprising how many insights can be uncovered that are not obvious, or outright counter-intuitive.

Let's go back to that GDP question. GDP estimates come out once a quarter, with several revisions. You would think that if GDP came in with a significant surprise on the upside on the first estimate, say up 0.8 percentage points more than consensus (indicating the economy was stronger than participants thought) the market would rise that day.

That sounds pretty intuitive, no? Turns out, the opposite is true.

This has happened seven times since 2001, and each time the S&P 500 has declined on that day. Every time.

The opposite is true as well: the S&P usually went up when the GDP was notably more disappointing than expectations, though the correlation was not as strong.

Why is that? My guess is that there's at least partly a "Fed effect," that this is an indication the markets are very much addicted to cheap money. If the news on the economy is good, traders assume there will be less stimulus; it it's bad, they assume there will be more.

What does this mean for our coverage of the markets? It means we will be using Kensho analytics throughout the day to show trading relationships that may not have been obvious in the past.

There's something else that we can use this for: big data analytics is very good at proving or disproving old wives' tales. Whether you are talking about fundamental or technical analysis, there is an awful lot of trader lore out there that, if held up to a microscope, may not be trader lore for very long.

For example, a couple months ago the 50-day moving average of the Russell 2000 crossed the 200-day moving average to the downside, a much-feared technical pattern known as the "Death Cross." There was much discussion of this on-air, as well as in print.

The Russell did decline that day, but the historical pattern is very mixed. This has happened 20 times since 1988, and five days later the Russell has been down 55 percent of the time, up 45 percent. That is a fairly mixed result, though the downs are somewhat bigger than the ups.

But two months later, the Russell has been UP 63 percent of the time. In other words, for most intermediate-term investors, simply holding would have been better than selling immediately.

To show some of these relationships, we will be unveiling a Kensho Stats Box that will come up as others are doing a hit with Kensho-related ideas. We will do the same for text in We might show what happens to ExxonMobil's stock in the past 10 years the day after its analyst meeting, or show what stocks have the greatest move on a day when Industrial Production numbers are much stronger than expected.

As part of this, NBC Universal News Group is making an investment in Kensho.

We are about to enter an era where Big Data analytics is going to democratize stock market analysis.

The bottom line: CNBC can now answer many of the questions it has been addressing for years in a more factual and systematic way.

Read MoreReading big data tea leaves on market moves

Kensho CEO Dan Nadler will appear on "Squawk on the Street" at 9:30 AM ET.

CNBC's parent NBCUniversal is an investor in Kensho, and the companies have a content-sharing arrangement.