Trend Without Hiccups - A Kalman Filter Approach

35 Pages Posted: 21 Mar 2016 Last revised: 26 Apr 2016

See all articles by Eric Benhamou

Eric Benhamou

AI For Alpha; LAMSADE- Paris Dauphine University

Date Written: April 12, 2016

Abstract

Have you ever felt miserable because of a sudden whipsaw in the price that triggered an unfortunate trade? In an attempt to remove this noise, technical analysts have used various types of moving averages (simple, exponential, adaptive one or using Nyquist criterion). These tools may have performed decently but we show in this paper that this can be improved dramatically thanks to the optimal filtering theory of Kalman filters (KF). We explain the basic concepts of KF and its optimum criterion. We provide a pseudo code for this new technical indicator that demystifies its complexity. We show that this new smoothing device can be used to better forecast price moves as lag is reduced. We provide 4 Kalman filter models and their performance on the SP500 mini-future contract. Results are quite illustrative of the efficiency of KF models with better net performance achieved by the KF model combining smoothing and extremum position.

Keywords: Kalman filter, systematic trading, moving average crossover, filtering, managed futures, CTA

JEL Classification: G02, G1, G13, G14

Suggested Citation

Benhamou, Eric, Trend Without Hiccups - A Kalman Filter Approach (April 12, 2016). Available at SSRN: https://ssrn.com/abstract=2747102 or http://dx.doi.org/10.2139/ssrn.2747102

Eric Benhamou (Contact Author)

AI For Alpha ( email )

35 boulevard d'Inkermann
Neuilly sur Seine, 92200
France

HOME PAGE: http://aiforalpha.com

LAMSADE- Paris Dauphine University ( email )

Place du Marechal de Lattre de Tassigny
Pais, 75016
France

HOME PAGE: http://www.lamsade.dauphine.fr/wp/miles/

Do you have a job opening that you would like to promote on SSRN?

Paper statistics

Downloads
2,618
Abstract Views
5,946
rank
5,885
PlumX Metrics