Quantitative finance mentality for success [closed]

Question

I have a strong statistical background (particularly in Time Series analysis) and previously have spent a lot of time modelling sports, Baseball in particular. After reading "Analysis of Financial Time Series" by Ruey S. Tsay, I have become interested in quantitative finance.

I'd like to know the mentality that quants have when it comes to the stock market. What I mean by this is what is the general idea to be successful. I'm not asking exactly HOW to do it but merely what to focus on. For example to be successful with Baseball modelling I focused on predicting the distribution of competing teams' runs.

I saw a comment here by Matt Wolf

If I have to summarize my take on financial markets then I would say success has 
everything to do with managing risk in smart ways as well as seizing opportunities in
times of market inefficiencies and it has very little to nothing to do with forecasting 
the future.

I understand that risk must be managed in smart ways and clearly to make any sort of expected profit, the only way to do this is to capitalise on market inefficiencies. However I do not get the part to do with forecasting the future. Surely this is necessary! Does it mean that success is not about POINT forecasts of the future but instead distributional forecasts e.g. option pricing seems all about distributional forecasting.

What I took away from it was that you shouldn't try to predict stock movements by some ARMA, ARIMA or a more general dependency equation or have I completely missed the point?

Answer 1

This is a very subjective question. One thing you need to understand is that there are many types of quants and it is not always about predicting the future returns.

Many quantitative analysts are involved in market-making, this is where you sell products at a slight cost to customers and try to stay more or less neutral to market moves. When you read about most of models that are discussed based on the non-arbitrage principle and replication, these models are used to find the fair price to quote to the customer. To simplify, it does not matter if the price will realise statistically if you can replicate the price via a hedge as the cost of the product will be the cost of the hedge. Most of the option models used for pricing are about finding a sensible interpolation/extrapolation for maturities/strikes that are not liquid in the market and producing hedges to manage the risk in order to lock the customer's margin.

Some other people are involved in proprietary strategies, this is what most of people not working in finance believe that traders are doing: making money out of the market. Even in this topic, people are not always using forecasts, you could be using arbitrages where by using a combination of trades you could be locking money.

However it is true that some quants or traders will try to forecast a relationship, it could be anything like a pairs to trade which is statistically mean reverting, a relationship that leads to abnormal positive returns, noticing that the series has momentum, using regime switching to find periods where the momentum exists, ... etc.

So even though you could specialise in forecasts, there are other ways to make money out of the market.