Category: Investing Insight

Investing insight to make you a better investor.

RSI through a Support Vector Machine, Part Deux

Yesterday, we asked a question: How would an SVM (Support Vector Machine) train if we gave it a 14-day RSI and 50-day SMA of the Nifty index? The goal was to use the SVM to first see if it can figure out a relationship between RSI and NIFTY and then check if we can turn that into a set of trading rules.

If you look at the predictions that the SVM gave for 2006, you can see two distinct areas where it went short (red contours) and where it went long (blue contours.) But the funny thing is, it went long when RSI > 50 (when the market is supposed to be overbought) and short when RSI < 40 (supposed to be oversold.)

svm-rsi-nifty-2006

The kicker is that it followed the trend (x-axis) more than RSI (y-axis). In terms of predictive power, trend seems to be way more powerful than RSI, at least for the year 2006.

To check if we can actually setup any trading rules (trend x RSI = 4 combinations for buy/sell), we ran yearly training data through an SVM to check if there were any stable relationships. Here’s the video:

The contours change year to year, with little stability between them. Basically, a trading strategy based on RSI is going to be random.

Related: Using SMA to Reduce Volatility of Returns

Mangling RSI through a Support Vector Machine

Conventional wisdom has it that RSI values over 70 to represent overbought market conditions and under 30 to represent oversold market conditions. But where did these numbers, 70 and 30, come from? We already tested two naive RSI strategies that bombed spectacularly. We were curious as to what an SVM (Support Vector Machine) would do if we gave it a 14 day RSI and 50-day SMA of the Nifty index. This is what came out of it:

svm-rsi-nifty

The bifurcation between long and short is pretty well defined. And is seems that trend overshadows RSI. Is RSI even relevant?

Fly or Die: Last Year’s Diwali Picks

It is that time of the year again when brokerage houses try and pick stocks for “muhurat trading.” Let’s see how they fared with their 2013 picks. NIFTY is up +27% since last Diwali.

Kotak Securities

Kotak picked 11 stocks that returned about +50%. Sharpe: 0.16732

kotak's 2013 Diwali picks

Microsec

Microsec picked 9 stocks that returned about +37%. Sharpe: 0.12822; but their portfolio has been pummeled lately.

microsec's 2013 Diwali picks

Globe

Globe’s 10 stocks returned about +37% but with a much lower Sharpe (0.11445) compared to Kotak and Microsec. It hit its peak sometime in July and its been sliding since then.

globe's 2013 Diwali Picks

Prabhudas Lilladher

Prabhudas Lilladher picked 4 stocks. Got to admire their courage here. +45% since Diwali, Sharpe: 0.15509.

Prabhudas Lilladher's 2013 Diwali stock picks

2014 Picks

We have created new themes to track brokers’ 2014 Diwali picks. Kotak, Globe and ET have published their recommendations so far.

You can find all Broker Recommendations here.

Are we setup up for a bond rally?

ICICI came out with an interesting note on why they expects Indian bonds to rally. They outline 5 factors:

  1. Improving current account balance
  2. Falling inflation
  3. Fiscal consolidation
  4. Rising savings rate
  5. Substantial FII inflows

Related: Long-term Gilt Funds, where we layout the same thesis.


 
 
You can run our comparison tool here: FundCompare
 
 
 

Please get in touch with Shyam for advice on investing in mutual funds.
You can either WhatsApp him or call him at 080-2665-0232.
He is an AMFI registered IFA who can advice you on IDBI, Mirae, HDFC, ICICI Pru, UTI and Birla Sun Life funds.