{"paper":{"title":"Stock Market Prediction Using Node Transformer Architecture Integrated with BERT Sentiment Analysis","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"An integrated node transformer and BERT sentiment model forecasts one-day stock prices at 0.80 percent MAPE on S&P 500 stocks.","cross_cats":["cs.AI","q-fin.ST"],"primary_cat":"cs.LG","authors_text":"Hussein Al Osman, Mahtab Haj Ali, Mohammad Al Ridhawi","submitted_at":"2026-03-06T05:15:22Z","abstract_excerpt":"Stock market prediction presents considerable challenges for investors, financial institutions, and policymakers operating in complex market environments characterized by noise, non-stationarity, and behavioral dynamics. Traditional forecasting methods, including fundamental analysis and technical indicators, often fail to capture the intricate patterns and cross-sectional dependencies inherent in financial markets. This paper presents an integrated framework combining a node transformer architecture with BERT-based sentiment analysis for stock price forecasting. The proposed model represents "},"claims":{"count":4,"items":[{"kind":"strongest_claim","text":"Experiments conducted on 20 S&P 500 stocks spanning January 1982 to March 2025 demonstrate that the integrated model achieves a mean absolute percentage error (MAPE) of 0.80% for one-day-ahead predictions, compared to 1.20% for ARIMA and 1.00% for LSTM.","source":"verdict.strongest_claim","status":"machine_extracted","claim_id":"C1","attestation":"unclaimed"},{"kind":"weakest_assumption","text":"The graph edges and social-media sentiment signals extracted by BERT provide stable, non-spurious predictive information that generalizes beyond the specific 1982-2025 training window and is not an artifact of data leakage or post-hoc feature selection.","source":"verdict.weakest_assumption","status":"machine_extracted","claim_id":"C2","attestation":"unclaimed"},{"kind":"one_line_summary","text":"The node transformer with BERT sentiment integration achieves 0.80% MAPE for one-day stock price forecasts on 20 S&P 500 stocks from 1982-2025, outperforming ARIMA and LSTM by capturing inter-stock dependencies and sentiment signals.","source":"verdict.one_line_summary","status":"machine_extracted","claim_id":"C3","attestation":"unclaimed"},{"kind":"headline","text":"An integrated node transformer and BERT sentiment model forecasts one-day stock prices at 0.80 percent MAPE on S&P 500 stocks.","source":"verdict.pith_extraction.headline","status":"machine_extracted","claim_id":"C4","attestation":"unclaimed"}],"snapshot_sha256":"3ba9b9d4306b477512015142d2e2415583bed49ff22a51cd2d74e86d2836d548"},"source":{"id":"2603.05917","kind":"arxiv","version":3},"verdict":{"id":"84004454-7127-4c66-924f-4168ef40cf5a","model_set":{"reader":"grok-4.3"},"created_at":"2026-05-15T14:42:03.190981Z","strongest_claim":"Experiments conducted on 20 S&P 500 stocks spanning January 1982 to March 2025 demonstrate that the integrated model achieves a mean absolute percentage error (MAPE) of 0.80% for one-day-ahead predictions, compared to 1.20% for ARIMA and 1.00% for LSTM.","one_line_summary":"The node transformer with BERT sentiment integration achieves 0.80% MAPE for one-day stock price forecasts on 20 S&P 500 stocks from 1982-2025, outperforming ARIMA and LSTM by capturing inter-stock dependencies and sentiment signals.","pipeline_version":"pith-pipeline@v0.9.0","weakest_assumption":"The graph edges and social-media sentiment signals extracted by BERT provide stable, non-spurious predictive information that generalizes beyond the specific 1982-2025 training window and is not an artifact of data leakage or post-hoc feature selection.","pith_extraction_headline":"An integrated node transformer and BERT sentiment model forecasts one-day stock prices at 0.80 percent MAPE on S&P 500 stocks."},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2603.05917/integrity.json","findings":[],"available":true,"detectors_run":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938"},"references":{"count":0,"sample":[],"resolved_work":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","internal_anchors":0},"formal_canon":{"evidence_count":2,"snapshot_sha256":"9b886b13a254cca4ee0c696809e0b86a6912ece7bd4967c1c8c5847d6290fcb6"},"author_claims":{"count":0,"strong_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"builder_version":"pith-number-builder-2026-05-17-v1"}