Archive

Archive for October, 2014

Day Trading Model Draft

October 30, 2014 Leave a comment

Teasers…

The SPX model accuracy (since 2010 test set) for correctly predicting positive/negative days:

es_model110514

actual_pred_LR_model103014

corrplot_daily_LR_model103014

Does (or soon “DID” ) QE lead to Positive Up Days in the Market?

October 25, 2014 Leave a comment

 

Just a simple but rather data preparation intensive study shows that the day of POMO did not necessarily lead to a green SPX day. The below plot shows a green SPX day & a day with POMO. If each occurred we get “TRUE”.

From this source QE started on 2008-12-15 which is the start date of this analysis to current day 2014-10-24″.
pomo_102514

Next I may examine if “front-running” the scheduled POMO had an effect by seeing if there were gap ups before the day of POMO. I may also gauge the magnitude of POMO’s impact on the up days.

 

* The information received by subscribers is for their personal use. Investing involves a great deal of risk, including the loss of all or a portion of your investment, as well as emotional distress. Nothing contained herein should be construed as a warranty of investment results. All risks, losses and costs associated with investing, including total loss of principal, are your responsibility.

Categories: Public Posts Tags: , , , , , ,

My First SVM Model

October 22, 2014 Leave a comment

 

 

svm_daily_APM_102214As a learning exercise/practice I created a very simple SVM model using the ksvm function under the kernlab package.

The predictors I used were: VIX, Crude, Gold and Previous Day’s Close (factor).

The results were factors either returning 1 or 0 if the following day’s close was higher than the previous.

The train/test data set start date is 2007-12-31. I first tried data partitioning (75/25) the train and test sets in a random fashion irrespective of time-series. Then I tried testing it in slices (75/25) so time was continuous. Results were very little changed.

Here is how the SVM model performed using those 4 variables:

The results were fairing unimpressive but better than 50/50 is a great start.

svm_model102414

 

Sentiment Signals & SPX Returns

October 16, 2014 Leave a comment

bull_bear_ratio_spx101614bull_bear_ratio_spx2_101614bull_bear_ratio_spx3_101614bull_bear_spx3_101614bull_bear_spx5_101614

Categories: Public Posts Tags: , , , , ,

NYSE Advance/Decline & SPX

October 16, 2014 Leave a comment

Here is a test to see if there any correlation between NYSE Advance Decline Ratio and SPX returns. SPX Returns from left to right are ordered: that same day, 1 day out, 2 days out. 3 days out, 4 days out.

As you can see there is very little correlation in general.

NYSE_AD_SPX101614

SPX October Returns Distribution Since 1950

October 15, 2014 Leave a comment

October historically can be a crazy month for selling/pullbacks and volatility
Oct_Dist_Ret101514

 

What happens after SPX falls more than 5% (Open-Low) in Oct?

oct_lo5_101514

Some plots between SPX & VIX, P/C, etc…

October 14, 2014 Leave a comment

VIX_SPX101414

index_pc_spx101414spx_dax101414

Categories: Public Posts Tags: , , , ,