A relative information approach to financial time series analysis using binary $N$-grams dictionaries

Abstract

Here we present a novel approach to statistical analysis of financial time series. The approach is based on $n$-grams frequency dictionaries derived from the quantized market data. Such dictionaries are studied by evaluating their information capacity using relative entropy. A specific quantization of (originally continuous) financial data is considered: so called binary quantization. Possible applications of the proposed technique include market event study with the $n$-grams of higher information value. The finite length of the input data presents certain computational and theoretical challenges discussed in the paper. also, some other versions of a quantization are discussed.

13 pages, 7 figures

References in corpus (3)

• Quantifying reflexivity in financial markets: towards a prediction of flash crashes
• Carbon-dioxide emissions trading and hierarchical structure in worldwide finance and commodities markets
• Market behavior and performance of different strategy evaluation schemes