{"id":5634,"date":"2025-11-10T15:47:43","date_gmt":"2025-11-10T06:47:43","guid":{"rendered":"https:\/\/www.waseda.jp\/fcom\/riba\/?p=5634"},"modified":"2025-11-10T15:52:25","modified_gmt":"2025-11-10T06:52:25","slug":"2025%e5%b9%b411%e6%9c%8824%e6%97%a5%e6%9c%88-%e3%81%ab%e7%94%a3%e7%a0%94%e8%ac%9b%e6%bc%94%e4%bc%9a%e3%80%8cwaseda-organizational-and-financial-economics-seminar-adding-noise-to-reduce-noise-a-co","status":"publish","type":"post","link":"https:\/\/www.waseda.jp\/fcom\/riba\/news\/5634","title":{"rendered":"2025\u5e7411\u670824\u65e5(\u6708) \u306b\u7523\u7814\u8b1b\u6f14\u4f1a\u300cWaseda Organizational and Financial Economics Seminar : Adding Noise to Reduce Noise: A Counter-Intuitive Approach to Stock Return Prediction \u300d\u304c\u958b\u50ac\u3055\u308c\u307e\u3059\u3002"},"content":{"rendered":"

\u300cAdding Noise to Reduce Noise: A Counter-Intuitive Approach to Stock Return Prediction\u300d\uff0a\u82f1\u8a9e\u3067\u306e\u3054\u5831\u544a<\/h3>\n
\n\n\n\n\n\n\n\n\n\n
\u65e5\u6642<\/th>\n2025\u5e7411\u670824\u65e5\uff08\u6708\uff0913:10\uff5e14:50<\/td>\n<\/tr>\n
\u958b\u50ac\u65b9\u6cd5<\/th>\n\u2460\u5bfe\u9762 \uff0a11\u53f7\u99288\u968e814\u6559\u5ba4\u306b\u304a\u8d8a\u3057\u304f\u3060\u3055\u3044\u3002
\n\u2461Zoom\uff0a\u304a\u7533\u8fbc\u307f\u5b8c\u4e86\u306e\u81ea\u52d5\u8fd4\u4fe1\u30e1\u30fc\u30eb\u306b\u3066\u3001\u53c2\u52a0\u7528URL\u3092\u304a\u77e5\u3089\u305b\u3044\u305f\u3057\u307e\u3059\u3002<\/td>\n<\/tr>\n
\u5bfe\u8c61<\/th>\n\u5b66\u751f\u30fb\u6559\u8077\u54e1\u30fb\u4e00\u822c<\/td>\n<\/tr>\n
\u8b1b\u6f14\u8005<\/th>\n\u00a0\u5f8c\u85e4\u3000\u664b\u543e \u6c0f
\n\uff08Professor, College of Business, The University of Rhode Island\uff09<\/td>\n<\/tr>\n
\u8981\u65e8<\/th>\nThis seminar introduces a new approach that, paradoxically, enhances the accuracy of cross-sectional stock-return predictions by deliberately adding random noise.
\nIn high-dimensional prediction settings, traditional regularization methods such as Ridge, Lasso, and PLS have been widely employed. However, these methods often produce negative out-of-sample R^2 values, making reliable prediction difficult in practice. To address this challenge, the study proposes two noise-based approaches\u2014noise injection and noise augmentation\u2014and demonstrates their effectiveness in stabilizing coefficient estimates and improving predictive performance.
\nThese methods are closely related to the phenomenon of \u201cbenign overfitting\u201d recently highlighted in the machine-learning literature and are consistent with the emerging view that dense models, rather than sparse ones, may yield superior out-of-sample forecasting results.
\nThe central theme of the study is a seemingly paradoxical mechanism: strategically adding noise to a model induces implicit regularization and improves out-of-sample predictive accuracy. A related paper, “Does Noise Hurt Economic Forecasts?” by Liao et al. (2024), provides evidence for the usefulness of noise augmentation in economic forecasting, though the theoretical rationale remains complex. We extend this insight to the more complex and inherently noisy domain of stock-return prediction and confirm its empirical validity. Furthermore, we introduce a more intuitive noise-injection method, clarify its relation to noise augmentation, and discuss the role and implications of noise in an accessible manner.
\nOverall, our results suggest that noise can function not merely as an error term but as a design element that improves the structure of predictive models. We hope this unconventional approach will open new possibilities for high-dimensional financial forecasting.<\/td>\n<\/tr>\n
\u4e16\u8a71\u4eba<\/th>\n\u5bae\u5cf6 \u82f1\u662d\uff08\u65e9\u7a32\u7530\u5927\u5b66\u5546\u5b66\u5b66\u8853\u9662 \u6559\u6388\uff09<\/td>\n<\/tr>\n
\u53c2\u52a0\u7533\u3057\u8fbc\u307f\u65b9\u6cd5<\/th>\n\u53c2\u52a0\u306f\u3053\u3061\u3089<\/a>\u304b\u3089\u304a\u7533\u8fbc\u307f\u304f\u3060\u3055\u3044\u3002\u203b11\u670820\u65e5\uff08\u6728\uff0917:00\u7de0\u5207<\/td>\n<\/tr>\n
\u5171\u50ac<\/th>\n\u65e9\u7a32\u7530\u5927\u5b66\u5546\u5b66\u90e8\u30fb\u7523\u696d\u7d4c\u55b6\u7814\u7a76\u6240\u30fb\u8c37\u5ddd\u5be7\u5f66\u5206\u79d1\u4f1a<\/td>\n<\/tr>\n<\/tbody>\n<\/table><\/div>\n

 <\/p>\n","protected":false},"excerpt":{"rendered":"

\u300cAdding Noise to Reduce Noise: A Counter-Intuitive Approach to Stock Return Prediction\u300d\uff0a\u82f1\u8a9e\u3067\u306e\u3054\u5831\u544a \u65e5\u6642 2025\u5e7411\u670824\u65e5 […]<\/p>\n","protected":false},"author":3,"featured_media":0,"comment_status":"closed","ping_status":"closed","sticky":false,"template":"","format":"standard","meta":{"_acf_changed":false,"footnotes":""},"categories":[1],"tags":[24],"class_list":["post-5634","post","type-post","status-publish","format-standard","hentry","category-news","tag-events"],"acf":[],"_links":{"self":[{"href":"https:\/\/www.waseda.jp\/fcom\/riba\/wp-json\/wp\/v2\/posts\/5634","targetHints":{"allow":["GET"]}}],"collection":[{"href":"https:\/\/www.waseda.jp\/fcom\/riba\/wp-json\/wp\/v2\/posts"}],"about":[{"href":"https:\/\/www.waseda.jp\/fcom\/riba\/wp-json\/wp\/v2\/types\/post"}],"author":[{"embeddable":true,"href":"https:\/\/www.waseda.jp\/fcom\/riba\/wp-json\/wp\/v2\/users\/3"}],"replies":[{"embeddable":true,"href":"https:\/\/www.waseda.jp\/fcom\/riba\/wp-json\/wp\/v2\/comments?post=5634"}],"version-history":[{"count":1,"href":"https:\/\/www.waseda.jp\/fcom\/riba\/wp-json\/wp\/v2\/posts\/5634\/revisions"}],"predecessor-version":[{"id":5637,"href":"https:\/\/www.waseda.jp\/fcom\/riba\/wp-json\/wp\/v2\/posts\/5634\/revisions\/5637"}],"wp:attachment":[{"href":"https:\/\/www.waseda.jp\/fcom\/riba\/wp-json\/wp\/v2\/media?parent=5634"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/www.waseda.jp\/fcom\/riba\/wp-json\/wp\/v2\/categories?post=5634"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/www.waseda.jp\/fcom\/riba\/wp-json\/wp\/v2\/tags?post=5634"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}