{"id":"https://openalex.org/W7128518322","doi":"https://doi.org/10.20944/preprints202602.0692.v2","title":"Do Technical Indicators Improve Deep Learning Forecasts? An Empirical Ablation Study Across Asset Classes","display_name":"Do Technical Indicators Improve Deep Learning Forecasts? An Empirical Ablation Study Across Asset Classes","publication_year":2026,"publication_date":"2026-02-09","ids":{"openalex":"https://openalex.org/W7128518322","doi":"https://doi.org/10.20944/preprints202602.0692.v2"},"language":"en","primary_location":{"id":"doi:10.20944/preprints202602.0692.v2","doi":"https://doi.org/10.20944/preprints202602.0692.v2","is_oa":true,"landing_page_url":"https://doi.org/10.20944/preprints202602.0692.v2","pdf_url":null,"source":{"id":"https://openalex.org/S6309402219","display_name":"Preprints.org","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":null,"host_organization_name":null,"host_organization_lineage":["https://openalex.org/P4310310987"],"host_organization_lineage_names":["Multidisciplinary Digital Publishing Institute"],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"acceptedVersion","is_accepted":true,"is_published":false,"raw_source_name":null,"raw_type":"posted-content"},"volume":null,"type":"preprint","is_traditional":true,"indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://doi.org/10.20944/preprints202602.0692.v2","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5128123501","display_name":"Nabeel Ahmad Saidd","orcid":"https://orcid.org/0009-0003-2373-9991","observed_orcids":["https://orcid.org/0009-0003-2373-9991"]},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Nabeel Saidd","raw_affiliation_strings":["Independent Researcher , India;"],"raw_orcid":"https://orcid.org/0009-0003-2373-9991","affiliations":[{"raw_affiliation_string":"Independent Researcher , India;","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":0,"corresponding_author_ids":["https://openalex.org/A5128123501"],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11326","display_name":"Stock Market Forecasting Methods","score":1.0,"subfield":{"id":"https://openalex.org/subfields/1803","display_name":"Management Science and Operations Research"},"field":{"id":"https://openalex.org/fields/18","display_name":"Decision Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},"topics":[{"id":"https://openalex.org/T11326","display_name":"Stock Market Forecasting Methods","score":1.0,"subfield":{"id":"https://openalex.org/subfields/1803","display_name":"Management Science and Operations Research"},"field":{"id":"https://openalex.org/fields/18","display_name":"Decision Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},{"id":"https://openalex.org/T10047","display_name":"Financial Markets and Investment Strategies","score":0.0,"subfield":{"id":"https://openalex.org/subfields/2003","display_name":"Finance"},"field":{"id":"https://openalex.org/fields/20","display_name":"Economics, Econometrics and Finance"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},{"id":"https://openalex.org/T11918","display_name":"Forecasting Techniques and Applications","score":0.0,"subfield":{"id":"https://openalex.org/subfields/1803","display_name":"Management Science and Operations Research"},"field":{"id":"https://openalex.org/fields/18","display_name":"Decision Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/technical-indicators","display_name":"technical indicators","score":0.9990000128746033},{"id":"https://openalex.org/keywords/recurrent-neural-networks","display_name":"recurrent neural networks","score":0.7950000166893005},{"id":"https://openalex.org/keywords/lstm","display_name":"LSTM","score":0.902999997138977},{"id":"https://openalex.org/keywords/gru","display_name":"GRU","score":0.9990000128746033},{"id":"https://openalex.org/keywords/feature-redundancy","display_name":"feature redundancy","score":0.7089999914169312},{"id":"https://openalex.org/keywords/feature-engineering","display_name":"feature engineering","score":0.6830000281333923},{"id":"https://openalex.org/keywords/ohlcv-data","display_name":"OHLCV data","score":0.718999981880188},{"id":"https://openalex.org/keywords/momentum-indicators","display_name":"momentum indicators","score":0.7250000238418579},{"id":"https://openalex.org/keywords/volatility-indicators","display_name":"volatility indicators","score":0.921999990940094},{"id":"https://openalex.org/keywords/asset-classes","display_name":"asset classes","score":0.5580000281333923},{"id":"https://openalex.org/keywords/cryptocurrency","display_name":"cryptocurrency","score":0.5350000262260437},{"id":"https://openalex.org/keywords/commodities","display_name":"commodities","score":0.8259999752044678},{"id":"https://openalex.org/keywords/foreign-exchange","display_name":"foreign exchange","score":0.9100000262260437},{"id":"https://openalex.org/keywords/directional-accuracy","display_name":"directional accuracy","score":0.44600000977516174},{"id":"https://openalex.org/keywords/ablation-study","display_name":"ablation study","score":0.5659999847412109}],"concepts":[{"id":"https://openalex.org/C149782125","wikidata":"https://www.wikidata.org/wiki/Q160039","display_name":"Econometrics","level":1,"score":0.6068000197410583},{"id":"https://openalex.org/C139945424","wikidata":"https://www.wikidata.org/wiki/Q1940696","display_name":"Mean squared error","level":2,"score":0.5784000158309937},{"id":"https://openalex.org/C91602232","wikidata":"https://www.wikidata.org/wiki/Q756115","display_name":"Volatility (finance)","level":2,"score":0.5501000285148621},{"id":"https://openalex.org/C12725497","wikidata":"https://www.wikidata.org/wiki/Q810247","display_name":"Baseline (sea)","level":2,"score":0.536899983882904},{"id":"https://openalex.org/C536366893","wikidata":"https://www.wikidata.org/wiki/Q66076","display_name":"Foreign exchange market","level":3,"score":0.5304999947547913},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.4943000078201294},{"id":"https://openalex.org/C169258074","wikidata":"https://www.wikidata.org/wiki/Q245748","display_name":"Random forest","level":2,"score":0.48989999294281006},{"id":"https://openalex.org/C117245426","wikidata":"https://www.wikidata.org/wiki/Q235038","display_name":"Technical analysis","level":2,"score":0.4878000020980835},{"id":"https://openalex.org/C9841139","wikidata":"https://www.wikidata.org/wiki/Q39099","display_name":"Renminbi","level":3,"score":0.45649999380111694},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.45329999923706055},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.43299999833106995},{"id":"https://openalex.org/C132964779","wikidata":"https://www.wikidata.org/wiki/Q2110223","display_name":"Raw data","level":2,"score":0.4020000100135803},{"id":"https://openalex.org/C70153297","wikidata":"https://www.wikidata.org/wiki/Q5591907","display_name":"Gradient boosting","level":3,"score":0.3815000057220459},{"id":"https://openalex.org/C2776988154","wikidata":"https://www.wikidata.org/wiki/Q66100","display_name":"Exchange rate","level":2,"score":0.3774999976158142},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3671000003814697},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.3560999929904938},{"id":"https://openalex.org/C120936955","wikidata":"https://www.wikidata.org/wiki/Q2155640","display_name":"Empirical research","level":2,"score":0.3546000123023987},{"id":"https://openalex.org/C76178495","wikidata":"https://www.wikidata.org/wiki/Q4808784","display_name":"Asset (computer security)","level":2,"score":0.34860000014305115},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.34689998626708984},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.34369999170303345},{"id":"https://openalex.org/C2983132609","wikidata":"https://www.wikidata.org/wiki/Q66076","display_name":"Foreign exchange","level":2,"score":0.3402999937534332},{"id":"https://openalex.org/C133199616","wikidata":"https://www.wikidata.org/wiki/Q25386885","display_name":"Empirical modelling","level":2,"score":0.336899995803833},{"id":"https://openalex.org/C46686674","wikidata":"https://www.wikidata.org/wiki/Q466303","display_name":"Boosting (machine learning)","level":2,"score":0.3345000147819519},{"id":"https://openalex.org/C163068380","wikidata":"https://www.wikidata.org/wiki/Q3409313","display_name":"Economic forecasting","level":2,"score":0.3059999942779541},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.3052000105381012},{"id":"https://openalex.org/C45804977","wikidata":"https://www.wikidata.org/wiki/Q7239673","display_name":"Predictive modelling","level":2,"score":0.30309998989105225},{"id":"https://openalex.org/C175223733","wikidata":"https://www.wikidata.org/wiki/Q1047888","display_name":"Spot contract","level":3,"score":0.29670000076293945},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.29490000009536743},{"id":"https://openalex.org/C60718061","wikidata":"https://www.wikidata.org/wiki/Q1414747","display_name":"Momentum (technical analysis)","level":2,"score":0.2913999855518341},{"id":"https://openalex.org/C180706569","wikidata":"https://www.wikidata.org/wiki/Q13479982","display_name":"Cryptocurrency","level":2,"score":0.2669000029563904},{"id":"https://openalex.org/C114289077","wikidata":"https://www.wikidata.org/wiki/Q3284399","display_name":"Statistical model","level":2,"score":0.260699987411499},{"id":"https://openalex.org/C202353208","wikidata":"https://www.wikidata.org/wiki/Q1167393","display_name":"Economic indicator","level":2,"score":0.25529998540878296}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.20944/preprints202602.0692.v2","doi":"https://doi.org/10.20944/preprints202602.0692.v2","is_oa":true,"landing_page_url":"https://doi.org/10.20944/preprints202602.0692.v2","pdf_url":null,"source":{"id":"https://openalex.org/S6309402219","display_name":"Preprints.org","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":null,"host_organization_name":null,"host_organization_lineage":["https://openalex.org/P4310310987"],"host_organization_lineage_names":["Multidisciplinary Digital Publishing Institute"],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"acceptedVersion","is_accepted":true,"is_published":false,"raw_source_name":null,"raw_type":"posted-content"},{"id":"doi:10.20944/preprints202602.0692.v1","doi":"https://doi.org/10.20944/preprints202602.0692.v1","is_oa":true,"landing_page_url":"https://doi.org/10.20944/preprints202602.0692.v1","pdf_url":"https://www.preprints.org/frontend/manuscript/b9c7ef1d31d8c808d4b55c9733a769f0/download_pub","source":{"id":"https://openalex.org/S6309402219","display_name":"Preprints.org","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":null,"host_organization_name":null,"host_organization_lineage":["https://openalex.org/P4310310987"],"host_organization_lineage_names":["Multidisciplinary Digital Publishing Institute"],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"acceptedVersion","is_accepted":true,"is_published":false,"raw_source_name":null,"raw_type":"posted-content"}],"best_oa_location":{"id":"doi:10.20944/preprints202602.0692.v2","doi":"https://doi.org/10.20944/preprints202602.0692.v2","is_oa":true,"landing_page_url":"https://doi.org/10.20944/preprints202602.0692.v2","pdf_url":null,"source":{"id":"https://openalex.org/S6309402219","display_name":"Preprints.org","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":null,"host_organization_name":null,"host_organization_lineage":["https://openalex.org/P4310310987"],"host_organization_lineage_names":["Multidisciplinary Digital Publishing Institute"],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"acceptedVersion","is_accepted":true,"is_published":false,"raw_source_name":null,"raw_type":"posted-content"},"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W7128518322.pdf","grobid_xml":"https://content.openalex.org/works/W7128518322.grobid-xml"},"referenced_works_count":1,"referenced_works":["https://openalex.org/W2964121744"],"related_works":["https://openalex.org/W4316012734","https://openalex.org/W7172341178","https://openalex.org/W4413178456","https://openalex.org/W4414332375","https://openalex.org/W7169508544","https://openalex.org/W4402673329","https://openalex.org/W4409686898","https://openalex.org/W4410428737","https://openalex.org/W2897244933","https://openalex.org/W4322747716"],"abstract_inverted_index":{"Technical":[0],"indicators":[1,40,146,254],"derived":[2],"from":[3,87],"historical":[4],"price":[5,43,157],"data":[6,86],"have":[7],"long":[8],"been":[9],"central":[10],"to":[11,19,49,89,137,155],"quantitative":[12],"trading":[13,311],"strategies,":[14],"yet":[15],"their":[16,272],"actual":[17],"contribution":[18],"modern":[20],"deep":[21,279],"learning":[22],"forecasting":[23,152],"models":[24,218],"remains":[25],"an":[26],"open":[27],"empirical":[28],"question.":[29],"This":[30],"study":[31],"presents":[32],"a":[33,96,119],"large-scale":[34],"ablation":[35],"analysis":[36],"examining":[37],"whether":[38],"technical":[39,145,289],"improve":[41,255],"next-day":[42],"prediction":[44,184,269],"when":[45],"used":[46],"as":[47,247],"inputs":[48],"recurrent":[50,280],"neural":[51,309],"networks.":[52],"We":[53],"conduct":[54],"500":[55],"controlled":[56],"experiments":[57],"across":[58,133],"10":[59],"assets":[60,262],"spanning":[61],"five":[62,134],"asset":[63,250],"classes\u2014commodities":[64],"(Crude":[65],"Oil,":[66],"Gold),":[67],"cryptocurrencies":[68],"(Bitcoin,":[69],"Ethereum),":[70],"equities":[71],"(Apple,":[72],"Microsoft),":[73],"foreign":[74],"exchange":[75,244],"(EUR/USD,":[76],"USD/JPY),":[77],"and":[78,100,118,130,171,313],"market":[79],"indices":[80],"(NASDAQ,":[81],"S&P":[82],"500)\u2014using":[83],"daily":[84],"OHLCV":[85,98,161],"2010":[88],"2025.":[90],"Five":[91],"feature":[92,306],"configurations":[93],"are":[94,236],"evaluated:":[95],"raw":[97,156],"baseline":[99,160,319],"four":[101,206],"indicator-augmented":[102,180],"variants":[103],"incorporating":[104],"momentum":[105],"(RSI,":[106],"Stochastic":[107],"Oscillator),":[108],"trend":[109],"(SMA,":[110],"EMA,":[111],"ADX,":[112],"MACD),":[113],"volatility":[114,253],"(ATR,":[115],"Bollinger":[116],"Bands),":[117],"combined":[120],"all-indicator":[121],"set.":[122],"Each":[123],"configuration":[124,162,181],"is":[125],"tested":[126],"with":[127,186],"both":[128],"LSTM":[129,225],"GRU":[131,217],"architectures":[132,235,281],"random":[135],"seeds":[136],"ensure":[138],"statistical":[139],"robustness.":[140],"Our":[141],"results":[142,301],"show":[143,209],"that":[144,278],"do":[147],"not":[148,237],"improve\u2014and":[149],"frequently":[150],"degrade\u2014":[151],"performance":[153,211,256],"relative":[154],"data.":[158],"The":[159,300],"achieves":[163],"the":[164,187,233,248,284,315],"lowest":[165],"mean":[166,173,268],"RMSE":[167,196,230,258],"(0.166":[168],"\u00b1":[169,177],"0.148)":[170],"highest":[172],"directional":[174,222],"accuracy":[175,223],"(55.7%":[176],"5.5%).":[178],"Every":[179],"produces":[182],"higher":[183,221,267],"error,":[185],"comprehensive":[188],"all-indicators":[189],"variant":[190],"exhibiting":[191],"statistically":[192,238],"significant":[193,210,239],"degradation":[194],"(34.6%":[195],"increase,":[197],"p":[198],"<":[199],"0.001,":[200],"Cohen\u2019s":[201],"d":[202],"=":[203,215,241],"\u22120.29).":[204],"All":[205],"indicator":[207,293],"categories":[208],"reduction":[212],"at":[213],"\u03b1":[214],"0.05.":[216],"achieve":[219],"marginally":[220],"than":[224,271],"(55.3%":[226],"vs.":[227],"51.0%),":[228],"although":[229],"differences":[231],"between":[232],"two":[234],"(p":[240],"0.846).":[242],"Foreign":[243],"stands":[245],"out":[246],"only":[249],"class":[251],"where":[252],"(4.2%":[257],"reduction),":[259],"while":[260],"high-volatility":[261],"(cryptocurrencies,":[263],"commodities)":[264],"exhibit":[265],"83%":[266],"error":[270],"low-volatility":[273],"counterparts.":[274],"These":[275],"findings":[276],"suggest":[277],"implicitly":[282],"learn":[283],"patterns":[285],"captured":[286],"by":[287],"conventional":[288],"indicators,":[290],"making":[291],"explicit":[292],"features":[294],"redun-":[295],"dant":[296],"or":[297],"even":[298],"harmful.":[299],"carry":[302],"practical":[303],"implications":[304],"for":[305],"engineering":[307],"in":[308,321],"network-based":[310],"systems":[312],"highlight":[314],"importance":[316],"of":[317],"rigorous":[318],"comparisons":[320],"applied":[322],"financial":[323],"machine":[324],"learning.":[325]},"counts_by_year":[],"updated_date":"2026-11-08T12:12:28.789561","created_date":"2026-02-11T00:00:00"}