題 目： Online-Purchasing Behavior Forecasting with a Firefly Algorithm-based SVM Model Considering Shopping Cart Use
主講人： 李健
時(shí) 間：2017年12月13日上午10:00
地 點(diǎn)：主樓418房間
主講人介紹：
李健，北京工業(yè)大學(xué)經(jīng)濟(jì)與偉德國(guó)際1946bv官網(wǎng)教授。研究方向：物流與供應(yīng)鏈管理、安全與應(yīng)急管理。入選2012年度教育部新世紀(jì)優(yōu)秀人才支持計(jì)劃，加拿大溫莎大學(xué)訪問(wèn)學(xué)者，兼任中國(guó)指揮與控制學(xué)會(huì)安全防護(hù)與應(yīng)急管理專業(yè)委員會(huì)總干事、中國(guó)系統(tǒng)工程學(xué)會(huì)監(jiān)事會(huì)監(jiān)事、湖南圖靈?；穬?chǔ)運(yùn)安全技術(shù)研究院智慧物流與智慧供應(yīng)鏈管理實(shí)驗(yàn)室主任等。在Omega、IJPE等國(guó)內(nèi)外主流重點(diǎn)期刊發(fā)表論文50余篇，出版英文專著 2 部。主持國(guó)家自然科學(xué)基金項(xiàng)目3項(xiàng)，參加國(guó)家重點(diǎn)研發(fā)計(jì)劃1項(xiàng)，參加國(guó)家自然科學(xué)基金重點(diǎn)項(xiàng)目1項(xiàng)。
內(nèi)容介紹：
Due to the complexity of the e-commerce system, a hybrid model for online-purchasing behavior forecasting is developed to predict whether or not a customer makes a purchase during the next visit to the online store based on the previous behaviors, i.e., online-purchasing behavior. The proposed model makes contributions to literature from two perspectives: (1) a classification model is proposed based on the “hybrid modeling” concept, in which an effective artificial intelligence (AI) technique of support vector machine (SVM) is employed for classification forecasting and further extended by introducing the promising AI optimization tool of firefly algorithm (FA), to solve the crucial but tough task of parameters selection, i.e., the FA-based SVM model; (2) an appropriate predictor set is carefully designed especially considering online shopping cart use which was otherwise neglected in existing models, apart from other common online behaviors, e.g., clickstream behavior, previous purchase behavior and customer heterogeneity. To verify the superiority of the proposed model, an online furniture store is focused on as study sample, and the empirical results statistically support that the proposed FA-based SVM model considering online shopping cart use significantly beat all benchmarking models (with other popular classification methods and/or different predictor sets) in terms of prediction accuracy。
（承辦：管理工程系，科研與學(xué)術(shù)交流中心）
