【摘要】：隨著互聯(lián)網(wǎng)技術(shù)的不斷進(jìn)步,眾籌平臺(tái)成為了一種新的網(wǎng)絡(luò)融資途徑。在眾籌平臺(tái)所產(chǎn)生的數(shù)據(jù)不斷增加的同時(shí),其數(shù)據(jù)效益并沒有成正比增長,因此產(chǎn)生了所謂的“信息超載”現(xiàn)象。個(gè)性化推薦系統(tǒng)從大量數(shù)據(jù)中挖掘用戶的興趣偏好,可以很好的解決這個(gè)問題,其在電子商務(wù)、社交媒體、廣告系統(tǒng)、搜索引擎等領(lǐng)域都取得了一定的成功。但是,在迅速發(fā)展的網(wǎng)絡(luò)眾籌領(lǐng)域,目前還未有眾籌網(wǎng)站為用戶提供專業(yè)的個(gè)性化推薦服務(wù)。本論文對(duì)眾籌平臺(tái)的整體情況進(jìn)行了分析,并對(duì)常用個(gè)性化推薦算法進(jìn)行了研究和比較,完成了對(duì)推薦系統(tǒng)輸入、輸出、以及推薦算法的選取與設(shè)計(jì)。同時(shí),本文應(yīng)用機(jī)器學(xué)習(xí)算法建立基于協(xié)同過濾的推薦系統(tǒng),并對(duì)其中存在的問題設(shè)計(jì)了相應(yīng)的改進(jìn)方案。一方面,本文針對(duì)數(shù)據(jù)稀疏性問題,設(shè)計(jì)了基于隱語義模型的協(xié)同過濾算法,利用統(tǒng)計(jì)學(xué)習(xí)方法解決模型最優(yōu)化問題。算法通過學(xué)習(xí)用戶評(píng)分?jǐn)?shù)據(jù)的特征,訓(xùn)練預(yù)測模型,得出預(yù)測評(píng)分后填充至原始評(píng)分矩陣,再以填充后的評(píng)分矩陣為數(shù)據(jù)源,基于協(xié)同過濾算法得到預(yù)測評(píng)分。另一方面,本文針對(duì)數(shù)據(jù)源單一帶來的冷啟動(dòng)問題,結(jié)合眾籌平臺(tái)的用戶評(píng)分與項(xiàng)目屬性特征,對(duì)協(xié)同過濾算法進(jìn)行了改進(jìn)。本文通過網(wǎng)絡(luò)通信技術(shù),獲取眾籌平臺(tái)用戶評(píng)分與項(xiàng)目屬性數(shù)據(jù),對(duì)推薦算法進(jìn)行了可行性驗(yàn)證,對(duì)特征學(xué)習(xí)模型中的參數(shù)進(jìn)行了調(diào)節(jié),并比較了改進(jìn)前后算法的平均絕對(duì)誤差與準(zhǔn)確度。經(jīng)過實(shí)驗(yàn)驗(yàn)證,本文所設(shè)計(jì)的眾籌平臺(tái)個(gè)性化推薦算法能夠提供精準(zhǔn)、快速的個(gè)性化推薦服務(wù),為用戶提供便利的同時(shí),也有利于眾籌平臺(tái)的發(fā)展。本論文提出的改進(jìn)算法,在一定程度上解決了數(shù)據(jù)稀疏性與冷啟動(dòng)問題,相較于傳統(tǒng)的推薦算法,預(yù)測的準(zhǔn)確度有了明顯的提升。該方案還可以根據(jù)用戶偏好的變化不斷學(xué)習(xí)修正,能夠取得不錯(cuò)的實(shí)時(shí)推薦效果。另外,本文采用實(shí)際運(yùn)行的眾籌平臺(tái)數(shù)據(jù)來完成算法的性能驗(yàn)證,具有更好的實(shí)用性。
[Abstract]:With the continuous progress of Internet technology, crowdfunding platform has become a new way of network financing. With the increasing data generated by crowdfunding platform, the data efficiency of crowdfunding platform is not proportional to the increase, so the so-called "information overload" phenomenon has emerged. Personalized recommendation system can solve this problem by mining users' interest preferences from a large number of data. It has achieved some success in e-commerce, social media, advertising system, search engine and other fields. However, in the rapidly developing field of network crowdfunding, there is no crowdfunding website to provide users with professional personalized recommendation services. In this paper, the overall situation of crowdfunding platform is analyzed, and the commonly used personalized recommendation algorithms are studied and compared, and the input and output of the recommendation system, as well as the selection and design of the recommendation algorithm are completed. At the same time, this paper uses machine learning algorithm to establish a recommendation system based on collaborative filtering, and designs the corresponding improvement scheme for the existing problems. On the one hand, aiming at the problem of data sparsity, a collaborative filtering algorithm based on implicit semantic model is designed, and the statistical learning method is used to solve the model optimization problem. By learning the characteristics of user scoring data and training the prediction model, the algorithm obtains the prediction score after filling into the original score matrix, and then takes the filled score matrix as the data source, and then obtains the prediction score based on collaborative filtering algorithm. On the other hand, aiming at the cold start problem caused by a single data source, combined with the user score and project attribute characteristics of crowdfunding platform, the collaborative filtering algorithm is improved. In this paper, the user score and project attribute data of crowdfunding platform are obtained by network communication technology, the feasibility of the recommendation algorithm is verified, and the parameters in the feature learning model are adjusted. The average absolute error and accuracy of the improved algorithm are compared. The experimental results show that the personalized recommendation algorithm of crowdfunding platform designed in this paper can provide accurate and fast personalized recommendation service, provide convenience for users, and is also conducive to the development of crowdfunding platform. The improved algorithm proposed in this paper solves the problem of data sparsity and cold start to a certain extent. Compared with the traditional recommendation algorithm, the accuracy of prediction is obviously improved. The scheme can also be revised according to the changes of user preferences, and can achieve a good real-time recommendation effect. In addition, this paper uses the actual crowdfunding platform data to verify the performance of the algorithm, which has better practicability.
【學(xué)位授予單位】：電子科技大學(xué)
【學(xué)位級(jí)別】：碩士
【學(xué)位授予年份】：2017
【分類號(hào)】：TP391.3;TP181

【參考文獻(xiàn)】

相關(guān)期刊論文 前10條

1 林少群;;互聯(lián)網(wǎng)金融融資模式剖析——源自中小微企業(yè)的P2P和眾籌實(shí)踐[J];宏觀經(jīng)濟(jì)管理;2017年S1期

2 周齊;;基于機(jī)器學(xué)習(xí)的推薦系統(tǒng)[J];電子技術(shù)與軟件工程;2016年24期

3 龔夢雪;;眾籌平臺(tái)評(píng)價(jià)體系研究——以淘寶眾籌為例[J];電子商務(wù);2016年09期

4 王升升;趙海燕;陳慶奎;曹健;;個(gè)性化推薦中的隱語義模型[J];小型微型計(jì)算機(jī)系統(tǒng);2016年05期

5 劉忠寶;;機(jī)器學(xué)習(xí)方法在個(gè)性化推薦系統(tǒng)中的應(yīng)用[J];情報(bào)探索;2016年04期

6 黃玲;周勤;;創(chuàng)意眾籌的異質(zhì)性融資激勵(lì)與自反饋機(jī)制設(shè)計(jì)研究——以“點(diǎn)名時(shí)間”為例[J];中國工業(yè)經(jīng)濟(jì);2014年07期

7 楊艷霞;于海平;陳燕;;基于Web挖掘的個(gè)性化推薦算法研究[J];計(jì)算機(jī)與數(shù)字工程;2014年04期

8 朱郁筱;呂琳媛;;推薦系統(tǒng)評(píng)價(jià)指標(biāo)綜述[J];電子科技大學(xué)學(xué)報(bào);2012年02期

9 王國霞;劉賀平;;個(gè)性化推薦系統(tǒng)綜述[J];計(jì)算機(jī)工程與應(yīng)用;2012年07期

10 馬宏偉;張光衛(wèi);李鵬;;協(xié)同過濾推薦算法綜述[J];小型微型計(jì)算機(jī)系統(tǒng);2009年07期

，

本文編號(hào)：2494183