{"paper_id":"2406.18206","title":"LSTM-ARIMA as a Hybrid Approach in Algorithmic Investment Strategies","authors":["Kamil Kashif","Robert Ślepaczuk"],"paper_date":"2024-06-26","paper_type":"empirical","paper_url":"https://arxiv.org/pdf/2406.18206v1","page_url":"https://thequant.space/flowcharts/lstm-arima-as-a-hybrid-approach-in-algorithmic-investment-st/","scores":{"empirical_rigor":6,"math_complexity":7,"quadrant":"Holy Grail"},"proposes":{"status":"available","statement":"The paper proposes a hybrid algorithmic investment strategy that combines LSTM and ARIMA models, called LSTM-ARIMA, to predict next‑day closing prices.","quote":"This study focuses on building an algorithmic investment strategy employing a hybrid approach that combines LSTM and ARIMA models referred to as LSTM-ARIMA.","summary":"This study focuses on building an algorithmic investment strategy employing a hybrid approach that combines LSTM and ARIMA models referred to as LSTM-ARIMA. This unique algorithm uses LSTM to produce final predictions but boosts the results of this RNN by adding the residuals obtained from ARIMA…","strategy":"LSTM-ARIMA"},"assumptions":{"status":"available","items":[{"assumption":"The walk‑forward optimization reduces over‑fitting risk.","type":"model","stated":"explicit","quote":"we use walk-forward optimization (WFO) as this technique reduces the risk of over-fitting to one specific sample of past returns."},{"assumption":"Predictions are made for the next day’s closing price using daily data.","type":"data","stated":"explicit","quote":"The algorithm predicted the next day’s closing price based on the historical data and was classified as a regression problem."},{"assumption":"ARIMA order d is set to 1 when modeling prices.","type":"model","stated":"explicit","quote":"In terms of stock forecasting, order d is usually set to 1 when we model the prices"},{"assumption":"The in‑sample window is 1250 trading days (1000 training, 250 validation).","type":"execution","stated":"explicit","quote":"We set the in-sample (IS) window to 1250 trading days where the training set is equal to 1000 trading and the validation set is equal to 250 trading days"}]},"datasets":{"status":"available","items":[{"name":"S&P 500","provider":"Yahoo Finance","kind":"market-prices","access":"public","period":"2000-01-03 to 2023-08-30","universe":null,"quote":"The testing architecture is based on the walk-forward procedure","known_id":"yahoo-finance"},{"name":"CAC 40","provider":"Yahoo Finance","kind":"market-prices","access":"public","period":"2000-01-03 to 2023-08-30","universe":null,"quote":"the ... CAC 40 equity index on 2004-12-28 and lasts until 2023-08-30.","known_id":"yahoo-finance"},{"name":"Yahoo Finance via yfinance API","provider":"Yahoo Finance","kind":"market-prices","access":"public","period":null,"universe":null,"quote":"We consider three equity indices in our research and the data is taken from Yahoo Finance using their yfinance API for Python.","known_id":"yahoo-finance"}],"known":[{"id":"yahoo-finance","name":"Yahoo Finance","provider":"Yahoo","kind":"market-prices","access":"public","quote":"Data Description We consider three equity indices in our research and the data is taken from Yahoo Finance using their yfinance API for Python.","mentions":3,"used_in":1},{"id":"cboe","name":"Cboe","provider":"Cboe Global Markets","kind":"options","access":"commercial","quote":"For the S&P 500 equity index, we use the CBOE’s VIX as the measure of volatility and for the FTSE 100 and CAC 40 equity index we use the annualized realized volatility with a historical window of 21 days, which is calculated using the following formula: annRV = sPN i=21 R2 t N × √ 252 (1) where: Rt - the daily returns t - the counter representing each trading day N - the number of trading days in our time frame Figur","mentions":2,"used_in":1}],"sample":{"start":"2005-01","end":"2023-08","market":"S&P 500 stocks","asset_class":"equities","frequency":"daily"},"data_resolution":"daily"},"transaction_costs":{"status":"available","modeled":"partial","headline_net_of_costs":false,"detail":null,"quote":null,"source":"front_matter","rule":"R1","candidates":{"front_matter":"partial","evidence_card":"unclear","evidence_card_quoted":false},"meaning":"costs appear only as a robustness check, a flat fee without spread or impact, or outside the headline numbers"},"results":{"status":"available","evaluation_type":"trading-pnl","findings":[{"finding":"LSTM-ARIMA outperforms all other models across all three equity indices according to the Modified Information Ratio.","kind":"performance","quote":"The findings conclude that the LSTM-ARIMA algorithm outperforms all the other algorithms across all the equity indices which confirms the strong potential behind hybrid ML-TS"},{"finding":"For FTSE 100 both Long‑Only and Long‑Short, LSTM-ARIMA achieves the highest IR** values, indicating best performance.","kind":"performance","quote":"Based on the evaluation of IR**metrics for both the Long-Only and Long-Short strategies, it can be deduced that the LSTM-ARIMA algorithm outperformed the other algorithms for the FTSE 100 equity index."},{"finding":"The hybrid model’s performance varies across assets, indicating lack of robustness to asset changes.","kind":"negative","quote":"Our hybrid model outperforms all the other models across all equity indices, though with varying performance metrics. The varying performance metrics across different assets indicate that our algorithms are not robust to changes in the asset."}],"reported_performance":{"strategy":"LSTM-ARIMA","sharpe":null,"sharpe_benchmark":null,"annual_return_pct":8.92,"total_return_pct":null,"max_drawdown_pct":56.62},"out_of_sample":{"method":"walk-forward","headline_out_of_sample":true}},"independent_evidence":{"status":"none_found","supports":[],"contradicts":[],"qualifies":[],"compared_with":15,"citations":{"cited_by_in_corpus":2,"by_independent_authors":0,"how_cited":{"used_as_baseline":0,"uses_method_or_data":0,"extends":0,"discusses_findings":0,"mentions":0,"unclassified":2},"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":"2026-11-14T18:07:14Z"},"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/"}