Paper: arXiv 2511.17479
Authors: Silvia Onofri, Andrey Shternshis, Stefano Marmi
Abstract
Markets efficiency implies that the stock returns are intrinsically unpredictable, a property that makes markets comparable to random number generators. We present a novel methodology to investigate ultra-high frequency financial data and to evaluate the extent to which tick by tick returns resemble random sequences. We extend the analysis of ultra high-frequency stock market data by applying comprehensive sets of randomness tests, beyond the usual reliance on serial correlation or entropy measures. Our purpose is to extensively analyze the randomness of these data using statistical tests from standard batteries that evaluate different aspects of randomness. We illustrate the effect of time aggregation in transforming highly correlated high-frequency trade data to random streams. More specifically, we use many of the tests in the NIST Statistical Test Suite and in the TestU01 battery (in particular the Rabbit and Alphabit sub-batteries), to prove that the degree of randomness of financial tick data increases together with the increase of the aggregation level in transaction time. Additionally, the comprehensive nature of our tests also uncovers novel patterns, such as non-monotonic behaviors in predictability for certain assets. This study demonstrates a model-free approach for both assessing randomness in financial time series and generating pseudo-random sequences from them, with potential relevance in several applications.
Complexity vs Empirical Score
- Math Complexity: 8.0/10
- Empirical Rigor: 3.0/10
- Quadrant: Lab Rats — high math complexity, limited empirical testing
Why this score: The paper involves high mathematical complexity through the application of advanced statistical randomness test suites (NIST, TestU01) and probabilistic hypothesis testing, but the empirical component is primarily methodological and descriptive, lacking specific backtesting protocols, dataset details, or implementation-heavy validation for trading strategies.
Research Flowchart
flowchart TD
A["Research Goal<br>Assess randomness of tick-by-tick returns<br>and effect of time aggregation"] --> B
subgraph B ["Methodology"]
direction LR
B1["NIST Test Suite<br>Serial Correlation, Entropy"] --> B2["TestU01 Battery<br>Rabbit & Alphabit"] --> B3["Ultra-HF Financial Data"]
end
B --> C
subgraph C ["Data & Processing"]
C1["Stock Transaction Data"] --> C2["Time Aggregation<br>Transforming high-frequency<br>to various time intervals"]
end
C --> D
subgraph D ["Computational Process"]
D1["Apply Tests<br>on aggregated streams"] --> D2["Compare Results<br>across aggregation levels"]
end
D --> E
subgraph E ["Key Findings & Outcomes"]
E1["Increased randomness<br>with aggregation"]
E2["Novel patterns<br>e.g., non-monotonic predictability"]
E3["Model-free approach<br>for randomness assessment"]
end
Evidence Card
What the authors claim, on what data, and who has checked it. Read from the paper's own text by a language model: every quote is verbatim, nothing was re-run. How to read this card
Proposes
We propose a model‑free methodology to assess randomness in ultra‑high‑frequency financial tick data and to generate pseudo‑random sequences from aggregated price strings.
Source sentence
We present a novel methodology to investigate ultra-high frequency financial data and to evaluate the extent to which tick by tick returns resemble random sequences. Our purpose is to extensively analyze the randomness of these data using statistical tests from standard batteries that evaluate different aspects of randomness.
Assumes 2
- Markets are efficient, implying that stock returns are intrinsically unpredictable. market
Source sentence
Markets efficiency implies that the stock returns are intrinsically unpredictable, a property that makes markets comparable to random number generators.
- Price series can be converted into binary strings for randomness testing. data
Source sentence
Our methodology enables the generation of ℓsub-sequences at each aggregation level ℓ.
Data
- LOBSTER limit order book data order-book public
Source sentence
We analyze data from limit order books obtained from LOBSTER (www.lobsterdata.com). Our study covers 80 trading days between 01-08-2022 and 21-11-2022.
Costs
Not applicable
Finds 3
- The degree of randomness of financial tick data increases as the aggregation level in transaction time grows. statistical
Source sentence
More specifically, we use many of the tests in the NIST Statistical Test Suite and in the TestU01 battery (in particular the Rabbit and Alphabit sub-batteries), to prove that the degree of randomness of financial tick data increases together with the increase of the aggregation level in transaction time. The threshold of 2 then represents α = 0.01: if −log10(pj) is under the threshold, this means that the test has
- Non‑monotonic predictability patterns are observed for certain assets, with predictability sometimes peaking at intermediate aggregation levels before decreasing. statistical
Source sentence
Additionally, the comprehensive nature of our tests also uncovers novel patterns, such as non-monotonic behaviors in predictability for certain assets. However, novel methods and tests sometimes reveal exceptions; for instance, there are cases where even at high aggregation levels the result of tests reveals predictability. 3.
- For some high‑activity stocks such as AAPL and TSLA, predictability persists even at high aggregation levels, likely due to their high trade frequency. statistical
Source sentence
For example, many tests for AAPL and TSLA highlight predictability also at high aggregation levels (see e.g. Figures 2, 3 and 4). We attribute this persistent predictability to their high trading activity: AAPL and TSLA have an average of respectively 6 and 8 trades per second (whereas CCL and LLY 14 Figure 3: Results of ApproximateEntropy test from NIST STS applied to AAPL, CCL, INTC and SPY data. on average have
Checked by others
No other paper in the archive has been found to support or contradict these findings (compared with 16 related papers). Coverage is partial, so this is neither replication nor refutation.
Extracted 2026-11-14 · same card as JSON · A language model chose these items: check the source sentence before relying on one.
Cited References (52)
- A Statistical Test Suite for Random and Pseudorandom Number Generators for Cryptographic Applications (2010)
- Limit order books (2013) — link
- Patterns in stock market movements tested as random number generators (2013)
- On random number generators and practical market efficiency — → 2305.17419
- Nonlinear dynamics and stock returns (1989)
- Market efficiency and random number generators in Solvency II (2022)
- Testing market efficiency on the Johannesburg Stock Exchange using the overlapping serial test (2016)
- Chaos and nonlinear dynamics: application to financial markets (1991)
and 44 more
- On bitcoin as a public randomness source (2015)
- Random Number Generation Based on Cryptocurrency Prices and Linear Feedback Shift Register (2024)
- ENT : A Pseudorandom Number Sequence Test Program (2008) — link
- String ENT test suite: ENT B attery revisited for efficient P value computation (2023)
- TestU01: A C Library for E mpirical T esting of R andom N umber G enerators (2007)
- TestU01: A software library in ANSI C for empirical testing of random number generators, User’s Guide (2013) — link
- Th 'e orie de la sp 'e culation (1900)
- CHAPTER 2 - How Markets Slowly Digest Changes in Supply and Demand (2009) — link
- The Econometrics of Ultra-High-Frequency Data (2000) — link
- The Long Memory of the Efficient Market (2004) — link
- Statistical properties of stock order books: empirical results and models (2002) — link
- Fluctuations and response in financial markets: the subtle nature of `random’ price changes (2003) — link
- Efficient Capital Markets: A Review of Theory and Empirical Work (1970) — link
- Quantis QRNG USB — link
- Price predictability at ultra-high frequency: Entropy-based randomness test — → 2312.16637
- A statistical test of market efficiency based on information theory (2023)
- Measuring market efficiency: The Shannon entropy of high-frequency financial time series (2022)
- Entropy and Efficiency of the ETF Market (2020) — link
- On Information and Sufficiency (1951) — link
- A mathematical theory of communication (1948) — link
- A computational view of market efficiency (2011)
- A computational definition of financial randomness (2014)
- Algorithmic trading and financial forecasting using advanced artificial intelligence methodologies (2022)
- Artificial intelligence applied to stock market trading: a review (2021)
- A singular value decomposition entropy approach for testing stock market efficiency (2021) — link
- Relative cluster entropy for power-law correlated sequences (2022)
- A nnouncement of P roposal to R evise S pecial P ublication 800-22 R evision 1a (2022) — link
- On the use of financial data as a random beacon (2010)
- The Ergodic Theory of Discrete Sample Paths (1996)
- Limit Distributions for a Statistical Estimate of the Entropy (1974) — link
- The informational efficiency: the emerging markets versus the developed markets (2009) — link
- Crude oil market efficiency: An empirical investigation via the Shannon entropy (2012) — link
- The adaptive markets hypothesis (2004) — link
- Empirical properties of asset returns: stylized facts and statistical issues (2001) — link
- An Investigation of Transactions Data for NYSE Stocks (1985) — link
- Randomness beacons from financial data in the presence of an active attacker (2025)
- On random number generators and practical market efficiency — → 2305.17419
- Patterns in stock market movements tested as random number generators (2013)
- The inefficiency of cryptocurrency and its cross-correlation with Dow Jones Industrial Average (2018)
- A visual analysis method of randomness for classifying and ranking pseudo-random number generators (2021)
- Beware of linear congruential generators with multipliers of the form a=$\pm$2 q$\pm$2 r (1999)
- A statistical test suite for random and pseudorandom number generators for cryptographic applications (2001)
- Randomness of möbius coefficients and Brownian motion: Growth of the Mertens function and the Riemann hypothesis (2021)
- Random factorizations and Riemann’s hypothesis (1944) — link
3 of 52 cited works are in the corpus; resolved via arXiv source bundles, Semantic Scholar and OpenAlex. Corpus-wide: 2596 linked papers.