- 關(guān)于我們
- 針對(duì)假冒留學(xué)監(jiān)理網(wǎng)的聲明
- 留學(xué)熱線:4000-315-285
留學(xué)中介口碑查詢
專業(yè):商業(yè)
項(xiàng)目類型:國外小組科研
開始時(shí)間:2024年12月21日
是否可加論文:是
項(xiàng)目周期:7周在線小組科研學(xué)習(xí)+5周不限時(shí)論文指導(dǎo)學(xué)習(xí)
語言:英文
有無剩余名額:名額充足
建議學(xué)生年級(jí):大學(xué)生
是否必需面試:否
適合專業(yè):軟件工程商業(yè)分析機(jī)器學(xué)習(xí)金融學(xué)數(shù)據(jù)科學(xué)數(shù)據(jù)分析人工智能風(fēng)險(xiǎn)管理商業(yè)統(tǒng)計(jì)編程語言
地點(diǎn):復(fù)旦大學(xué)·生命科學(xué)創(chuàng)新實(shí)踐基地
建議選修:Python數(shù)據(jù)處理及其數(shù)學(xué)原理
建議具備的基礎(chǔ):對(duì)商業(yè)分析、商業(yè)統(tǒng)計(jì)、數(shù)據(jù)科學(xué)、數(shù)據(jù)處理、機(jī)器學(xué)習(xí)、深度學(xué)習(xí)、信息安全等專業(yè)和課題感興趣,相關(guān)專業(yè)或希望在相關(guān)領(lǐng)域深入學(xué)習(xí)的學(xué)生 具備Python基礎(chǔ)知識(shí),數(shù)學(xué)邏輯良好的學(xué)生優(yōu)先
產(chǎn)出:7周在線小組科研學(xué)習(xí)+5周不限時(shí)論文指導(dǎo)學(xué)習(xí) 共125課時(shí) 項(xiàng)目報(bào)告 優(yōu)秀學(xué)員獲主導(dǎo)師Reference Letter EI/CPCI/Scopus/ProQuest/Crossref/EBSCO或同等級(jí)別索引國際會(huì)議全文投遞與發(fā)表指導(dǎo)(可用于申請(qǐng)) 結(jié)業(yè)證書 成績單
項(xiàng)目背景:如何運(yùn)??數(shù)據(jù)及數(shù)據(jù)分析來形成預(yù)測模型已經(jīng)成為?個(gè)決策者在當(dāng)今互聯(lián)?經(jīng)濟(jì)的商業(yè)世界中必不可少的研究技能。以數(shù)理編程為?段,從數(shù)據(jù)分析出發(fā),以決策優(yōu)化來創(chuàng)造價(jià)值。比如,抖音快手會(huì)根據(jù)觀看視頻的數(shù)據(jù),收集觀眾的喜好,推薦不同的短視頻;網(wǎng)易云會(huì)統(tǒng)計(jì)聽眾的聽歌歷史,為不同的人量身定制歌單。商業(yè)數(shù)據(jù)分析的本質(zhì)是要為企業(yè)解決實(shí)際問題,既要了解市場,又要懂得分析方法,最重要的是能落地。項(xiàng)目將帶領(lǐng)學(xué)生學(xué)習(xí)機(jī)器學(xué)習(xí)算法的基本問題和步驟、了解其在數(shù)據(jù)挖掘領(lǐng)域的應(yīng)用,并充分利用所學(xué)知識(shí)解決客戶細(xì)分及反欺詐等實(shí)際問題。 In the world of Big Data, data has become a strategic resource that enterprises and society focus on. How can we use mature statistical analysis and data mining techniques to conduct efficient business analysis to maximize benefits? Databases provide data management techniques, while machine learning and statistics provide data analysis techniques. The project will lead students to learn machine learning algorithms, understand its application in the field of data mining, and solve practical problems such as customer segmentation and anti-fraud.
項(xiàng)目介紹:機(jī)器學(xué)習(xí)是使用統(tǒng)計(jì)建模算法來解決大型數(shù)據(jù)集的實(shí)際定量問題,并用于研究和實(shí)際解決常見或不尋常的商業(yè)問題。 本項(xiàng)目將帶領(lǐng)學(xué)生學(xué)習(xí)監(jiān)督學(xué)習(xí)與無監(jiān)督學(xué)習(xí)、過度擬合、訓(xùn)練數(shù)據(jù)、測試數(shù)據(jù)、驗(yàn)證數(shù)據(jù)、線性回歸和邏輯回歸、決策樹算法、提升樹算法、隨機(jī)森林、神經(jīng)網(wǎng)絡(luò)、聚類算法、特征選擇、正則化、主成分分析、擬合優(yōu)度度量、分類變量編碼、模糊匹配等機(jī)器學(xué)習(xí)基礎(chǔ)知識(shí)及數(shù)據(jù)挖掘經(jīng)典算法,項(xiàng)目結(jié)束時(shí)提交項(xiàng)目報(bào)告,進(jìn)行成果展示。
Machine Learning is the use of statistical modeling algorithms to solve practical quantitative problems around large data sets. The mainline practices are building either supervised or unsupervised algorithms that can be used for data analysis, predictions, and forecasts. The main processes in machine learning are data exploration, analysis, cleaning, building expert variables, applying linear or nonlinear fitting algorithms, and evaluation of results. There are many kinds of statistical and machine learning algorithms including linear and logistic regressions, decision trees, boosted trees, random forests, neural nets, support vector machines, k nearest neighbors, Bayesian networks, and clustering algorithms.
項(xiàng)目大綱:監(jiān)督學(xué)習(xí)與無監(jiān)督學(xué)習(xí)、過度擬合、數(shù)據(jù)檢測、線性回歸 ML modeling basics; training/testing/validating data sets; linear regression 非線性機(jī)器學(xué)習(xí)算法 Nonlinear ML algorithms 聚類、特征選擇、正則化、主成分分析、擬合優(yōu)度度量 Clustering, curse of dimensionality, feature selection, regularization, PCA, model measures of goodness 數(shù)據(jù)準(zhǔn)備及預(yù)處理 Data preparation 機(jī)器學(xué)習(xí)、數(shù)據(jù)挖掘在客戶細(xì)分及反欺詐等實(shí)際問題中的運(yùn)用 ML applications, such as in marketing segmentation, fraud score 項(xiàng)目回顧與成果展示 Program Review and Presentation 論文輔導(dǎo) Project Deliverables Tutoring