28 Sep 2018
Intraday execution invo
lves buying or se
lling a certain quantity of shares in a given time period. Backtesting is rea
lly important in trying to improve execution a
lgorithms. This post explores a backtesting for a simplified scenario.
28 Jul 2018
I recent
ly looked into RPC frameworks (gRPC, Thrift, and RPyC) when I was looking to migrate a set of python c
lasses to a service. I am summarizing my initia
l findings in this post. Because I most
ly use python for everything, I am approaching these frameworks from that point of view.
24 May 2018
This paper suggests a way of using both historica
l prices and text data together for financia
l time series prediction. They ca
ll it Stocknet. There seems to be 2 major contributions here: (a) Encoding both market data and text data together, (b) VAE (Variationa
l AutoEncoder) inspired generative mode
l.
04 Apr 2018
Microbes are fascinating. They are intriguing. And we're just starting to find out the re
lationship they have with their hosts (us humans). I recent
ly read 'I contain mu
ltitudes' book. It turned out to be much better than my expectations. I attempt to highlight intriguing points from that book along with other things I picked e
lsewhere.
11 Feb 2018
Financia
l markets have been one of the earliest adopters of machine
learning (M
L). Peop
le have been using M
L to spot patterns in the markets since 1980s. Even though M
L has had enormous successes in predicting the market outcomes in the past, the recent advances in deep
learning haven’t he
lped financia
l market predictions much. Whi
le deep
learning and other M
L techniques have fina
lly made it possib
le for A
lexa, Goog
le Assistant and Goog
le Photos to work, there hasn’t been much progress when it comes to stock markets.
30 Dec 2017
Python - C++ bindings are usefu
l for severa
l reasons. Performance is one of them. Exposing existing C++ c
lasses to a python modu
le is another important reason.
14 Dec 2017
Factor-based strategies are very common in quant funds. Doing a good job of forecasting the fundamenta
ls direct
ly trans
lates into better returns in the factor strategies. The authors used the US company data from 1970 to 2017. They compare M
LP/RNN approach against the linear regression and a naive predictor.
11 Nov 2017
Reinforcement
Learning is a mathematica
l framework for experience-driven autonomous
learning. An R
L agent interacts with its environment and, upon observing the consequences of its actions, can
learn to a
lter its own behaviour in response to the rewards received. The goa
l of the agent is to
learn a p
olicy ππ that maximizes the expected return (cumulative, discounted reward).
19 Oct 2017
This is the second of a series of posts on the task of applying machine learning for intraday stock price/return prediction. Price prediction is extremely crucial to most trading firms. People have been using various prediction techniques for many years. We will explore those techniques as well as recently popular algorithms like neural networks. In this post, we will focus on applying neural networks on the features derived from market data.