Fixed Points in Self-Similar Analysis of Time Series

TL;DR

This paper explores two definitions of fixed points in self-similar analysis of time series, compares their practical equivalence in stock market data, and makes a forecast for March 1998 indices.

Contribution

It introduces and compares two fixed point definitions in self-similar time series analysis and applies them to stock market data for forecasting.

Findings

The two fixed point definitions are practically equivalent in stock market analysis.

Self-similar analysis can be used for stock market forecasting.

Forecasts were made for March 1998 stock indices.

Abstract

Two possible definitions of fixed points in the self-similar analysis of time series are considered. One definition is based on the minimal-difference condition and another, on a simple averaging. From studying stock market time series, one may conclude that these two definitions are practically equivalent. A forecast is made for the stock market indices for the end of March 1998.