{"paper_id":"2307.08853","title":"Comparative Analysis of Machine Learning, Hybrid, and Deep Learning Forecasting Models Evidence from European Financial Markets and Bitcoins","authors":["Apostolos Ampountolas"],"paper_date":"2023-07-17","paper_type":"empirical","paper_url":"https://arxiv.org/pdf/2307.08853v1","page_url":"https://thequant.space/flowcharts/comparative-analysis-of-machine-learning-hybrid-and-deep-l/","scores":{"empirical_rigor":7,"math_complexity":4,"quadrant":"Street Traders"},"proposes":{"status":"available","statement":"The paper proposes that the hybrid ETS-ANN model is the best‑performing forecasting approach for European stock indices and Bitcoin despite its moderate accuracy.","quote":"In this study, the results suggest that the hybrid ETS-ANN model is the best-performing model despite its moderate level of accuracy.","summary":"This study analyzes the transmission of market uncertainty on key European financial markets and the cryptocurrency market over an extended period, encompassing the pre, during, and post-pandemic periods. Daily financial market indices and price observations are used to assess the forecasting…","strategy":null},"assumptions":{"status":"available","items":[{"assumption":"Financial return series are stationary after log‑return transformation.","type":"statistical","stated":"explicit","quote":"To evaluate the study’s models, stationary data are required; hence, we computed the log returns and ran the augmented Dickey–Fuller (ADF) tests to test the unit root null hypothesis."},{"assumption":"Data are split into training and test sets using an 80:20 ratio.","type":"data","stated":"explicit","quote":"We split the dataset into two segments for each subperiod: a training set and a test set to assess the model’s forecasting performance, following a ratio of 80:20."},{"assumption":"Seasonal adjustments and min–max scaling are applied before model estimation.","type":"data","stated":"explicit","quote":"Before using the dataset for the forecasting models, the original series undergoes two pre-processing techniques: seasonal adjustments and scaling."},{"assumption":"Model hyperparameters for ARIMA and kNN are tuned per year and index, while ETS‑ANN uses the same hyperparameters across years.","type":"model","stated":"explicit","quote":"we used different hyperparameters for the ARIMA and kNN models based on the year and financial index in this study, we used the same hyperparameters across years for the hybrid ETS-ANN model."},{"assumption":"Error terms in ARIMA are white noise with Gaussian distribution, mean zero and constant variance.","type":"model","stated":"explicit","quote":"εt denotes the error sequence, which is considered a white noise process with a Gaussian distribution, specifically, the error sequence has a mean of zero and a constant variance of σ2."}]},"datasets":{"status":"available","items":[{"name":"BTC‑USD daily prices","provider":"cryptodatadownload.com","kind":"crypto-onchain","access":"public","period":"1 January 2018 to 31 December 2021","universe":"Bitcoin‑USD exchange rate","quote":"This study evaluated daily prices for the BTC-USD (data are publicly available at https://www.cryptodatadownload.com/data/"},{"name":"European stock market indices (FCHI, GDAXI, FTSE, SSMI, N100)","provider":"Yahoo Finance","kind":"market-prices","access":"public","period":"1 January 2018 to 31 December 2021","universe":"Major European stock exchanges","quote":"The daily price dataset was obtained from Yahoo Finance","known_id":"yahoo-finance"}],"known":[{"id":"yahoo-finance","name":"Yahoo Finance","provider":"Yahoo","kind":"market-prices","access":"public","quote":"The daily price dataset was obtained from Yahoo Finance (finance.yahoo.com, (accessed on 22 January 2023)) for the period that ranges from 1 Jan-Forecasting 2023, 1 4 uary 2018 to 31 December 2021.","mentions":1,"used_in":1}],"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":"front_matter","rule":"R1","candidates":{"front_matter":"n/a","evidence_card":"no","evidence_card_quoted":false},"meaning":"the paper reports no trading or execution result"},"results":{"status":"available","evaluation_type":"forecast-accuracy","findings":[{"finding":"For BTC‑USD, ETS‑ANN achieved the lowest MAPE (15.48%) over 2018‑2021, but overall accuracy was low.","kind":"predictive-accuracy","quote":"The best-performing model in this period is ETS-ANN, which achieves a MAPE of 15.48%, indicating a moderate accuracy level."},{"finding":"For GDAXI, ARIMA obtained the lowest MAPE (2.45%) for the whole sample, indicating good accuracy.","kind":"predictive-accuracy","quote":"The best-performing model is the ARIMA model, which achieves the lowest MAPE 2.45% and the lowest MAE, indicating a good level of accuracy."},{"finding":"Across most indices and sub‑periods, ARIMA and ETS‑ANN outperformed kNN, with ARIMA often ranking best.","kind":"performance","quote":"Overall, the ARIMA and ETS-ANN models performed better than the kNN model while evaluating the model’s accuracy."},{"finding":"The hybrid ETS‑ANN model is deemed the best‑performing overall despite moderate accuracy, as indicated by low MAPE values across sub‑periods.","kind":"performance","quote":"In conclusion, the results suggest that the ETS-ANN model is the best-performing model despite its moderate level of accuracy."},{"finding":"kNN showed superior performance for FTSE and SSMI during the pro‑COVID‑19 period (2020).","kind":"performance","quote":"the kNN model showed better results for the FTSE and SSMI indices during the pro‑COVID‑19 period."}],"reported_performance":null,"out_of_sample":{"method":"holdout","headline_out_of_sample":null}},"independent_evidence":{"status":"none_found","supports":[],"contradicts":[],"qualifies":[],"compared_with":29,"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":false,"code_url":null,"note":"No repository presented by the authors as their own was found in the paper. Absence here is not proof that no code exists."},"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":"2026-11-14T18:24:38Z"},"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/"}