講座題目：依據(jù)持倉(cāng)股票選擇公募基金：一種機(jī)器學(xué)習(xí)方法（Selecting mutual funds from the stocks they hold: a machine learning approach）

講座時(shí)間：2022年5月19日（星期四）10:00 – 11:30

主講人: 李斌，武漢大學(xué)經(jīng)濟(jì)與管理學(xué)院教授、博士生導(dǎo)師。金融研究中心主任，武漢大學(xué)教育發(fā)展基金會(huì)投資咨詢(xún)委員會(huì)委員，中國(guó)金融學(xué)年會(huì)理事，金融科技研究與教育五十人論壇成員，特許金融分析師（CFA）持證人。

研究領(lǐng)域：金融科技、投資管理和機(jī)器學(xué)習(xí)等，在《Journal of Accounting Research》《Artificial Intelligence》《Journal of Machine Learning Research》《管理科學(xué)學(xué)報(bào)》《中國(guó)工業(yè)經(jīng)濟(jì)》、ICML、IJCAI等金融會(huì)計(jì)和人工智能類(lèi)期刊會(huì)議上發(fā)表多篇論文；主持國(guó)家自然科學(xué)基金等項(xiàng)目，已結(jié)題自科基金青年項(xiàng)目后評(píng)估為特優(yōu)；研究成果獲得海通證券等轉(zhuǎn)載應(yīng)用，獲評(píng)中國(guó)金融學(xué)年會(huì)優(yōu)秀論文二等獎(jiǎng)等。

內(nèi)容簡(jiǎn)介：

We select mutual funds in real time by combining individual fund holdings and a large number (94) of stock characteristics to compute fund-level exposures to characteristics on the basis of the stocks they hold. The majority of funds are exposed---both positively and negatively---to approximately 40-50 characteristics. In addition, fund performance is non-linearly related to fund characteristics and their interactions. This feature proves important when we predict fund performance, as machine learning methods such as boosted regression trees (BRTs) significantly outperform standard linear frameworks. Our BRT-generated forecasts encompass the ones generated by the predictors of mutual fund performance that have been proposed in the literature so far.

會(huì)議接入方式：騰訊會(huì)議

會(huì)議號(hào)：787-555-249

會(huì)議密碼：220519