{"paper_id":"2512.17225","title":"Modelling financial time series with quantum field theory","authors":["Dimitrios Bachtis","David S. Berman","Arabella Schelpe"],"paper_date":"2025-12-19","paper_type":"empirical","paper_url":"https://arxiv.org/pdf/2512.17225v1","page_url":"https://thequant.space/flowcharts/modelling-financial-time-series-with-quantum-field-t/","scores":{"empirical_rigor":3,"math_complexity":9,"quadrant":"Lab Rats"},"proposes":{"status":"available","statement":"The paper proposes a disordered φ⁴ quantum field theory, equivalent to a Markov random field machine learning algorithm, to model and forecast financial time series.","quote":"In this manuscript we propose the ϕ4 quantum field theory, a system with Z2 symmetry and continuous degrees of freedom, to model and forecast empirical financial time series.","summary":"We use a φ^“4” quantum field theory with inhomogeneous couplings and explicit symmetry-breaking to model an ensemble of financial time series from the S&P 500 index. The continuum nature of the φ⁴ theory avoids the inaccuracies that occur in Ising-based models which require a discretization of the…","strategy":null},"assumptions":{"status":"available","items":[{"assumption":"The subset of selected stocks forms a market.","type":"market","stated":"explicit","quote":"We assume that the subset of stocks forms a market and calculate statistics, such as the market mean and kurtosis."},{"assumption":"Log‑returns are used as the time‑series representation.","type":"data","stated":"explicit","quote":"we consider the log-returns for the time series of a subset of V = 20 stocks from the S&P 500 index."},{"assumption":"A simple moving average of 250 trading days smooths short‑term fluctuations.","type":"data","stated":"explicit","quote":"To smooth out short-term fluctuations, we apply a simple moving average of 250 days to the data, which corresponds to one trading year."},{"assumption":"Training data precede prediction data chronologically.","type":"execution","stated":"explicit","quote":"The training set comprises the chronologically former values and the prediction set the most recent ones."},{"assumption":"Random subsets of stocks are used for finite‑size scaling analysis.","type":"statistical","stated":"explicit","quote":"We select V = 64 stocks from the S&P 500 index and calculate the average of their returns over 20 years at a fixed point in time."},{"assumption":"Scaling exponents are obtained by numerical fits on logarithmic axes.","type":"statistical","stated":"explicit","quote":"The results of the finite size scaling analysis are depicted on logarithmic axes in Fig. 3."}]},"datasets":{"status":"available","items":[{"name":"Subset of 20 S&P 500 stocks (log‑returns)","provider":"S&P 500 index","kind":"market-prices","access":"public","period":"01/01/2013 onward for 2000 trading days","universe":"20 S&P 500 constituents","quote":"The initial date for the time series is 01/01/2013 and we extend the time series for 2000 trading days in the past."},{"name":"Subset of 64 S&P 500 stocks (log‑returns)","provider":"S&P 500 index","kind":"market-prices","access":"public","period":"20‑year window ending 01/01/2023","universe":"64 S&P 500 constituents","quote":"We select V = 64 stocks from the S&P 500 index and calculate the average of their returns over 20 years at a fixed point in time: 01/01/2023."},{"name":"AAPL, MSFT, NVDA daily returns","provider":null,"kind":"market-prices","access":"public","period":null,"universe":"Three large‑cap US stocks","quote":"We train the model on a dataset comprising the returns for the time series of the AAPL, MSFT and NVDA stocks."}],"known":[],"sample":{"start":null,"end":null,"market":null,"asset_class":null,"frequency":null},"data_resolution":"daily"},"transaction_costs":{"status":"not_applicable","modeled":"n/a","headline_net_of_costs":null,"detail":null,"quote":null,"source":"evidence_card","rule":"R2","candidates":{"front_matter":"unclear","evidence_card":"n/a","evidence_card_quoted":true},"card_detail":null,"card_quote":"The purpose of this was to demonstrate that this approach has potential, not yet to present fully formulated investment strategies which could be employed in live trading.","meaning":"the paper reports no trading or execution result"},"results":{"status":"available","evaluation_type":"forecast-accuracy","findings":[{"finding":"The φ⁴ quantum field theory can reproduce higher‑order statistics such as market kurtosis, which Ising‑based binarized models cannot.","kind":"statistical","quote":"The ϕ4 quantum field theory is expressive enough to reproduce the higher-order statistics such as the market kurtosis, which can serve as an indicator of possible market shocks."},{"finding":"Finite‑size scaling yields exponents kwij = –0.96(1) and kai = –0.81(1) (and similar values for a 2013 date).","kind":"theoretical","quote":"through numerical fits we extract the values of two exponents kwij = −0.96(1) and kai = −0.81(1)."},{"finding":"Forecasting MAE for φ⁴ model is 0.019 versus 0.023 for a simple rescaled‑mean baseline, indicating slightly better performance.","kind":"predictive-accuracy","quote":"The mean absolute errors for the ϕ4 result and the rescaled mean prediction are 0.019 and 0.023, respectively. The ϕ4 result performs slightly better."},{"finding":"The scaling properties of weights and biases suggest exploitable market‑structure features for future investment strategies.","kind":"theoretical","quote":"The scaling results for the weights and biases of the theory hint at the possibility of uncovering features of market structure, which once more fully explored may be able to be exploited."},{"finding":"The model could be extended to predict option prices or to design transaction‑cost‑minimizing trajectories.","kind":"other","quote":"Finally, the model may have sufficient predictive power for more than one day ahead prediction and forecasts a full probability distribution, and so could be used to produce predictions for option prices, or in transaction cost minimizing trajectories [16]."}],"reported_performance":null,"out_of_sample":{"method":"holdout","headline_out_of_sample":null}},"independent_evidence":{"status":"none_found","supports":[],"contradicts":[],"qualifies":[],"compared_with":42,"citations":{"cited_by_in_corpus":0,"by_independent_authors":0,"how_cited":{"used_as_baseline":0,"uses_method_or_data":0,"extends":0,"discusses_findings":0,"mentions":0,"unclassified":0},"independent_papers":[],"scope":"Citations between papers in this corpus only; citations from outside it are not counted."}},"implementation":{"status":"available","public":true,"code_url":"https://github.com/dbachtis/phi4fin","note":null},"replication":{"status":"none_found","card":null,"note":"No replication of this paper has been run by thequant.space yet."},"extraction":{"text_source":"fulltext","model":"openai/gpt-oss-120b","version":1,"extracted_at":"2026-11-14T17:18:45Z"},"provenance":{"claims":"Everything here is what the authors state in the paper. Nothing was re-run or reproduced by the platform.","quotes":"Assumptions, datasets, cost detail and findings were extracted by a language model. Every quote is verbatim paper text. Where an item has `support`, \"full\" means every figure in it appears in the quoted sentences and \"partial\" means a figure is stated elsewhere in the paper; items with a figure found nowhere in the paper were discarded.","datasets_known":"datasets.known lists well-known vendors and public datasets by a stable id, found by a dictionary over the full text where the sentence says the data is used; it is independent of the model and covers only names in the dictionary.","flags":"transaction_costs.modeled, results.evaluation_type and results.out_of_sample.method are platform classifications (structured-decision models); see https://thequant.space/score-guide/#penalty-flags","comparisons":"supports / contradicts / qualifies are a language model's reading of two papers' quoted findings, restricted to closely related papers that share no author. They are pointers to read, not verified replications, and coverage is partial.","implementation":"code_url is a repository the paper itself presents as its own (rule-scored, ambiguous cases judged by a model), checked for liveness when it was recorded."},"docs":"https://thequant.space/agents/"}