Skip to content
#explainable ai Open access

The Period a Moving-Average Crossover Finds Is Made by the Ratio of the Two Periods: Holding the Ratio Fixed and Multiplying Both Periods by Eight Moves the Normalised Interval Only from 0.650 to 0.653 [F001]

Sep 2026 · Zenodo (CERN European Organization for Nuclear Research)

Abstract

二本の移動平均のクロスについて「この組み合わせは約N本の波を捉えている」と言われることがある。そのNを決めているのが相場なのか、二本の期間の選び方なのかを、ティックデータで測った。 四銘柄(USDJPY・EURUSD・GBPUSD・XAUUSD)の2019年から2024年までの1時間足で、連続するクロスの間隔の中央値を、三つの族について測った。比を4.0に固定したまま期間を8倍にすると、間隔を遅い期間で割った量は 0.650 から 0.653 へ 1.005倍しか動かない(相場に固有の周期があるなら 8.00倍になるはずである)。比を2.5に固定して5倍にしても 1.042倍である。一方、遅い期間を80に固定して比だけを16から2へ変えると、同じ量は 0.247 から 0.731 へ 2.962倍動く。 20/80 のクロス間隔の中央値は、四銘柄すべてで 53.0本であり、銘柄の間の幅は 0.0本である。 同じ測定を合成乱数(独立な正規増分の累積・20系列)で行うと 20/80 で 0.625 が出て、11セルでの実測との差の中央は 0.035 である。乱数の側でも三つの族の形がそのまま再現される。増分の大きさを100倍しても値は 0.000000 しか変わらず、クロスの間隔は尺度不変である。 ただし11セルすべてで実測は乱数より長い側にあり、比の中央は 1.060 である。2セルは20系列のばらつきの外に出る。本稿はこのずれを説明しない。 この論文の位置づけ:新しい数学定理も新しい法則も主張しない。単純移動平均、そのクロス、ランダムウォークはすべて既知である。特定の教材やその著者、販売元は主題ではなく、一切名指していない。本稿が測るのは間隔だけであり、その間隔から利益が出るか出ないかは扱わない。測定は日中・少数銘柄に限られ、月次の時系列モメンタムのようにより長い保有で文書化されている結果を否定するものではない。足は1時間足に固定しており、単純移動平均だけを扱っている。 作成にあたって:本稿の着想と内容は、著者自身の考察に基づくものです。文章の構成整理や英訳、集計に用いたスクリプトの作成には AI(大規模言語モデル)の助力を得ました。最終的な内容の解釈や誤りがあれば、それらはすべて著者の責に帰します。お気づきの点があれば、ご教示いただければ幸いです。 ----- It is sometimes said of a moving-average crossover that "this pair captures waves of about N bars." This paper measures, on tick data, whether that N is set by the market or by the choice of the two periods. Using one-hour bars for four series (USDJPY, EURUSD, GBPUSD, XAUUSD) from 2019 to 2024, the median interval between consecutive crossovers is measured across three families. Holding the ratio at 4.0 and multiplying both periods by 8 moves the interval divided by the slow period only from 0.650 to 0.653, a factor of 1.005 (a market-intrinsic period would give a factor of 8.00). Holding the ratio at 2.5 and multiplying by 5 gives 1.042. By contrast, holding the slow period at 80 and moving only the ratio from 16 to 2 moves the same quantity from 0.247 to 0.731, a factor of 2.962. The median crossing interval of the 20/80 pair is 53.0 bars in all four series, a spread of 0.0 bars. The same measurement on a synthetic random walk (cumulative independent normal increments, 20 realisations) gives 0.625 for 20/80, with a median difference of 0.035 across the eleven cells; the shape of all three families is reproduced. Multiplying the increment size by 100 changes the result by 0.000000, so the crossing interval is scale invariant. In all eleven cells, however, the measured value lies on the longer side of the random walk, with a median ratio of 1.060, and two cells fall outside the spread of the 20 realisations. This paper does not explain that offset. Scope of this paper: no new mathematical theorem and no new law is claimed. Simple moving averages, their crossovers, and random walks are all known. No real course, author, or vendor is the subject here, and none is named. Only the interval is measured; whether it yields a profit is not addressed. The measurement is intraday and covers few instruments, and does not contradict results documented at longer holding periods, such as monthly time-series momentum. Bars are fixed at one hour and only simple moving averages are treated. Acknowledgement: The ideas and content of this paper stem from the author's own considerations. Assistance from an AI (a large language model) was used for structuring, English translation, and writing the scripts used for the measurement. Any remaining errors or misinterpretations are solely the author's. Feedback and corrections are sincerely appreciated.

View source

Similar papers

#artificial intelligence Conference Open access Apr 2020

ECCOLA - a Method for Implementing Ethically Aligned AI Systems

The method, ECCOLA, is presented, which aims at making the high-level AI ethics principles more practical, making it possible for developers to more easily implement them in practice.

Ville Vakkuri, Kai-Kristian Kemell, P. Abrahamsson · 64 citations · ⚡6
#computer vision Review Apr 2024

AI-powered Code Review with LLMs: Early Results

The goal is to not only refine the accuracy of the LLM-based tool but also to underscore its potential in streamlining the software development lifecycle through proactive code improvement and education.

Z. Rasheed, Malik Abdul Sami, Muhammad Waseem et al. · 62 citations · ⚡3
#computer vision Open access Mar 2024

LLM-based agents for automating the enhancement of user story quality: An early report

The use of large language models to automatically improve the user story quality in Austrian Post Group IT agile teams is explored, with a reference model for an Autonomous LLM-based Agent System developed and implemented at the company.

Zheying Zhang, M. Rayhan, Tomas Herda et al. · 48 citations · ⚡4
#computer vision Review Mar 2024

System for systematic literature review using multiple AI agents: Concept and an empirical evaluation

This paper introduces a novel multi-AI-agent system designed to fully automate SLRs, and demonstrates how it substantially reduces the time and effort traditionally required for SLRs while maintaining comprehensiveness and precision.

Abdul Malik Sami, Z. Rasheed, Kai-Kristian Kemell et al. · 44 citations · ⚡2
#computer vision Feb 2024

Can Large Language Models Serve as Data Analysts? A Multi-Agent Assisted Approach for Qualitative Data Analysis

The proposed LLM-based multi-agent system automates qualitative data analysis process, creating opportunities for researchers and practitioners, and future improvements focus on enhancing multilingual performance and integrating continuous expert feedback.

Z. Rasheed, Muhammad Waseem, Aakash Ahmad et al. · 41 citations
#artificial intelligence Conference Open access Jun 2018

The Key Concepts of Ethics of Artificial Intelligence

It is suggested that the focus on finding keywords is the first step in guiding and providing direction for future research in the AI ethics field.

Ville Vakkuri, P. Abrahamsson · 39 citations · ⚡2

Related blog posts

Microsoft Research Blog Oct 7, 2026

Agent Lightning v1.0: A 3,500-Line Lightweight Agentic RL Framework for Training Agents with Real Harnesses

Training AI agents with reinforcement learning can be challenging because their tools, context, and decision-making are managed by complex frameworks. Agent Lightning connects existing agents to RL training, making it easier to improve them without rebuilding them. The post Agent Lightning v1.0: A 3,500-Line Lightweight Agentic RL Framework for Training Agents with Real Harnesses appeared first on Microsoft Research.

We use cookies to run the site and, with your consent, for analytics and to show ads. See our Cookie Policy.