{"paper_id":"2503.12648","title":"Realized Volatility Forecasting for New Issues and Spin-Offs using Multi-Source Transfer Learning","authors":["Andreas Teller","Uta Pigorsch","Christian Pigorsch"],"paper_date":"2025-03-16","paper_type":"empirical","paper_url":"https://arxiv.org/pdf/2503.12648v1","page_url":"https://thequant.space/flowcharts/realized-volatility-forecasting-for-new-issues-and-spin-offs/","scores":{"empirical_rigor":7.5,"math_complexity":7,"quadrant":"Holy Grail"},"proposes":{"status":"available","statement":"The paper proposes a model‑agnostic, instance‑based multi‑source transfer learning approach that selects source subsequences via DTW similarity to improve realized volatility forecasts for new issues and spin‑offs.","quote":"we propose an instance-based multi-source transfer learning approach that selects subsequences from complementary financial assets based on the dynamic time warping (DTW) distance between the new issue/spin-off and complementary data series.","summary":"Forecasting the volatility of financial assets is essential for various financial applications. This paper addresses the challenging task of forecasting the volatility of financial assets with limited historical data, such as new issues or spin-offs, by proposing a multi-source transfer learning…","strategy":null},"assumptions":{"status":"available","items":[{"assumption":"The main limitation for forecasting new issues is the lack of historical data at the beginning of an asset’s life cycle.","type":"data","stated":"explicit","quote":"It can be assumed that the main reason for this shortage in the existing research is the lack of historical data at the beginning of a financial asset’s life cycle."},{"assumption":"The transfer learning method can be applied to any forecasting model (model‑agnostic).","type":"model","stated":"explicit","quote":"Our proposed transfer learning approach has the advantage of being model-agnostic, meaning it can be applied to any type of model one might consider for forecasting realized volatility."},{"assumption":"Target and source data contain labeled volatility observations suitable for supervised learning.","type":"data","stated":"explicit","quote":"When predicting the 1-day-ahead volatility of new issues/spin-offs based on past volatility observations, we encounter data sets that inherently contain labeled data."},{"assumption":"Dynamic Time Warping distance is an appropriate similarity metric for selecting relevant source subsequences.","type":"statistical","stated":"explicit","quote":"After computing the DTW distance between the most recent target observations and each subsequence within U, we selectively transfer into the training data set DT only those subsequences whose DTW distance ranks below a predefined percentile ϵ."},{"assumption":"Only a minimal amount of target data (as little as the first trading day) is sufficient when combined with selected source data.","type":"data","stated":"implied","quote":"our approach necessitates only a minimal amount of target data and can be combined with any realized variance forecasting model."}]},"datasets":{"status":"available","items":[{"name":"Target new‑issue/spin‑off intraday price data","provider":"FirstRate Data LLC","kind":"market-prices","access":"commercial","period":"2010-2020","universe":"10 new issues and spin‑offs that entered the public market and were part of the S&P 500 on","quote":"As our primary target data set, we use 1-minute intraday stock price data obtained from FirstRate Data LLC on 10 new issues and spin-offs that entered the public market between 2010 and 2020 and were part of the S&P 500 index on November 1, 2022."},{"name":"Source S&P 500 intraday price data","provider":"FirstRate Data LLC","kind":"market-prices","access":"commercial","period":null,"universe":"66 additional S&P 500 stocks selected by market‑cap within each GICS sector","quote":"Furthermore, for our source data set, we consider the 1-minute intraday price data of 66 additional S&P 500 stocks. Again, the data is retrieved from FirstRate Data LLC."}],"known":[{"id":"cboe","name":"Cboe","provider":"Cboe Global Markets","kind":"options","access":"commercial","quote":"The V IX data has been retrieved from Cboe Exchange (2023).","mentions":2,"used_in":1},{"id":"yahoo-finance","name":"Yahoo Finance","provider":"Yahoo","kind":"market-prices","access":"public","quote":"The wide range of models developed to 3The earnings announcement schedule and HSI data has been retrieved from Yahoo Finance.","mentions":1,"used_in":1}],"sample":{"start":null,"end":null,"market":null,"asset_class":null,"frequency":null},"data_resolution":"unclear"},"transaction_costs":{"status":"not_applicable","modeled":"n/a","headline_net_of_costs":null,"detail":null,"quote":null,"source":"front_matter","rule":"R3","candidates":{"front_matter":"n/a","evidence_card":"n/a","evidence_card_quoted":false},"meaning":"the paper reports no trading or execution result"},"results":{"status":"available","evaluation_type":"forecast-accuracy","findings":[{"finding":"The multi‑source transfer learning approach outperforms models trained only on target data or on pooled target‑plus‑all‑source data.","kind":"performance","quote":"The results show that our transfer learning approach outperforms the alternative models and that the integration of complementary data is also beneficial immediately after the initial trading day of the new issue/spin-off."},{"finding":"Combining the transfer learning method with XGBoost yields the best forecasting performance among all model classes.","kind":"predictive-accuracy","quote":"our proposed transfer learning method in combination with XGBoost models shows superior forecasting performance compared to any other model class or training data set approach."},{"finding":"In the first 100‑day sample period, MTL models improve average MSE by up to 44.2% and average MAE by up to 23.2% relative to the naive‑pooling (NF) benchmark.","kind":"predictive-accuracy","quote":"In the first sample period, the MTL models yield improvements in forecast accuracy of up to 44.2% in the average MSE and up to 23.2% in the average MAE."},{"finding":"MTL models dominate across all individual 100‑day evaluation periods, consistently providing more accurate realized variance predictions than the NF approach.","kind":"performance","quote":"Every MTL model provides, on average, more accurate realized variance predictions than the NF in each sample period, considering both MSE and MAE."}],"reported_performance":null,"out_of_sample":{"method":"walk-forward","headline_out_of_sample":null}},"independent_evidence":{"status":"none_found","supports":[],"contradicts":[],"qualifies":[],"compared_with":35,"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":"2026-11-14T17:42:50Z"},"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/"}