Skip to content
All library documents

Bid-Ask Bounce, Midprice Returns, and Order-Book Dynamics

Article Quant Q&A · Author: user1050421
Read the original

Summary

The document describes bid-ask bounce in high-frequency data: trades alternating between bid and ask can make observed prices jump around the underlying market value. Taking log returns of midprices and features may reduce some nonstationarity, but the response does not claim this removes bid-ask bounce. It emphasizes that midprice changes and trade signs are jointly shaped by order-book activity.

The answer cautions against assuming recurrent neural networks perform well on transaction data, since trades arrive irregularly and the timing of liquidity supply and consumption carries information. It recommends considering order-book state directly, which may already encode much of the relevant history, and points to research on price formation, Markovian limit-order markets, and queue-reactive models. The response offers conceptual guidance rather than a concrete preprocessing recipe or tested forecast comparison. Its main practical lesson is to model the order book and event timing with care instead of relying on transformed prices and an assumed time-series architecture.

Key ideas

  • Alternation between bid-side and ask-side trades can create apparent price jumps in high-frequency observations.
  • Midprice log returns may help address nonstationarity but are not shown to eliminate bid-ask bounce.
  • Transaction arrivals are irregular, and the timing of liquidity provision and consumption contains information.
  • Order-book state can encode useful history, reducing the need to rely on recurrent models alone.
  • The response recommends studying order-book and queue dynamics but supplies no tested forecasting recipe.

Tags

High-frequency tradingMarket microstructureMachine learningExecution
Full text
# Getting over bid-ask bounce


# Getting over bid-ask bounce












One property of High-Frequency data is it's subject to bid-ask bounce.

Description : Unlike traditional data based on just closing prices, tick data carry additional supply-and-demand information in the form of bid and ask prices and offering sizes.

As a researcher, it can be an advantage because bid and ask quotes can carry valuable information about impending market moves.

However, bid and ask quotes are separated by a spread. Continuous movement from bid to ask and back introduces a jump process, difficult to deal with through many conventional models.

I am actually working on high-frequency trading project. At the beginning, I wanted to predict the price movement, but because the price is non-stationary and other reasons, it made the problem harder than I was expected. Now, instead of dealing with the price, I deal with the log-returns on the midprice (similar to the standard price) and the features.

Why am I talking of features?

For autoregressive problem, it is well known that RNN-LSTM perform pretty well on a time-series forecasting problem. As the midprices as well as the features are not stationary, then I applied the log-returns on all of them. I think it will be easier to approach the solution of my problem.

However, now, I think I face the problem of bid-ask bounce. How can I get over that setback? Does the log on the midprice is sufficient to face the bid-ask bounce problem?

## Answer by lehalle (score 2)

https://quant.stackexchange.com/a/79439

The joint dynamics of the mid price and the sign of the trades is a complex animal... you should respect its wild nature.

First, I suggest you have a look at this question Optimal Price Metric for High-Frequency Volatility: Executed Price, Mid Price, or Weighted Mid Price?.

Second, you seem to take as well-recognised that "RNN-LSTM perform pretty well [on returns of trades]". Be careful: generally LSTMs (or / and RNN) are used on uniformly sampled time series, and for sure it is not the case of transactions. Serial correlations between the arrival of liquidity (limit orders) and the consumption of liquidity tells us that the sampling if far from uniform: worst that that it contains information... (see the literature of Econophysicists, on Hawkes process in HF Finance, or have a look at L and Sophie Laruelle. Market microstructure in practice. World Scientific, 2nd Edition 2018)

I recommend to read Sirignano, Justin, and Rama Cont. "Universal features of price formation in financial markets: perspectives from deep learning." In Machine Learning and AI in Finance, pp. 5-15. Routledge, 2021. If you read it carefully, it will tell you the the recurrent aspect is not that useful: the state of the orderbook contains already a lot of information about its past .

That was already the message of Cont, Rama, and Adrien De Larrard. "Price dynamics in a Markovian limit order market." SIAM Journal on Financial Mathematics 4, no. 1 (2013): 1-25, and it has been continued in Huang, Weibing, L, and Mathieu Rosenbaum. "Simulating and analyzing order book data: The queue-reactive model" Journal of the American Statistical Association 110, no. 509 (2015): 107-122.

Putting all this knowledge in a end-to-end pipeline should provide what you need.

Shown in full with attribution under the source's licence. Licence: CC BY-SA 4.0 (Stack Exchange)

This summary was written by Stratmill's research agent from the original; it is not a copy of the source.