Understanding The Probabilities For Crude Oil

|
Includes: BNO, CRUD, DBO, DNO, DTO, DWTI, OIL, OLEM, OLO, SCO, SZO, TWTI, UCO, USL, USO, UWTI
by: Dave Allen

Summary

Crude Oil is down 35% over the past 6 months.

We’ve seen Crude trade down in a “similar” fashion like this 31 times since 1983.

Only one time out of 31, has Crude traded down more than 5% in next 3 months, the average 3 month return of all 31 similar historical instances is 14.9%.

"One Look is Worth a Thousand Words" - Piqua Auto Supply House, 1913 Newspaper Ad

Take a look at the chart below, which shows the 3 month forward returns of each of the 31 most similar historical instances of the current 6 month price trend in Crude Oil:

(SOURCE: EidoSearch data dated 12/1/14)

We are not in uncharted territory with the current drop in Crude. In fact, as mentioned above, we've seen this happen 31 times with high statistical similarity over the past 30 years. Out of these 31 instances, only one time has Crude Oil continued down from here more than 5%. As shown in the graphic, Crude dropped another -22.2% from October 1993 to January 1994.

This is more than an interesting historical study. Many financial technology providers and services allow investors to find "analogs" of similar historical instances, and these stats are valuable. We often espouse the benefits of using history as an objective gauge for the future. What sets this apart is the ability to turn these historical statistics into validated probabilities.

It has been easier to answer the question, "when has Crude Oil traded down 35% over a 6 month period historically and what happens next?". This is typically done by formulaically describing a % move up or down over a specified period. Again, valuable information but this is not predictive analytics. This is using historical data to provide interesting statistics. What this approach is not able to capture is the path of the 35% drop.

Consider these three scenarios, 1) Crude drops 35% in the first month and then languishes for the next 5 months and 2) Crude trades sideways for 5 ½ months and then drops 35% in two weeks and 3) Crude gradually trades down 35% over 6 months. These are three very different scenarios, with investors feeling very different about their positions, about where Crude Oil prices are headed and what actions they plan to take. So, while this provides some interesting statistics and historical analogs for a gauge, there are limitations that market participants accept.

The difference is the ability of using predictive analytics technology to mathematically describe the pattern and trajectory of these current market trends and rapidly and accurately find the most similar historical instances in seconds. I am not after simple statistics, but rather relationships in the data that I have validated to be predictive to forward outcomes

The unique characteristics and trajectory of patterns, and the ability to find these patterns and data relationships through mathematics contains discerning power. Or, as I say, "the Path Matters".

Per the chart back up at the top, there's only one instance historically out of 31 with similar paths/patterns that is down more than 5% in the next 3 months. What do the historical forward return distributions of these similar patterns tell us about the probabilities?

There's 85% probability Crude Oil will be above its current price in 3 months (return and volatility projection below):

(SOURCE: EidoSearch data dated 12/1/14)

The charts below show the current 6 month price trend in Crude (upper left), and the 5 most similar matches historically that in part make up our historical return distributions:

(SOURCE: EidoSearch data dated 12/1/14)

In summary, only one time out of 31, has Crude traded down more than 5% in the next 3 months and, the average 3 month return of all 31 statistically similar historical instances is 14.9%.

Disclosure: The author has no positions in any stocks mentioned, and no plans to initiate any positions within the next 72 hours.

The author wrote this article themselves, and it expresses their own opinions. The author is not receiving compensation for it. The author has no business relationship with any company whose stock is mentioned in this article.