本文選題：最大熵模型　切入點(diǎn)：Page　出處：《湘潭大學(xué)》2017年碩士論文　論文類型：學(xué)位論文

【摘要】：NBA作為全球最具影響力的籃球頂級(jí)賽事聯(lián)盟,吸引著全世界籃球愛好者的關(guān)注,一直受大眾追捧。球隊(duì)之間的實(shí)力非常接近,以及大量隨機(jī)性因素使得比賽結(jié)果的預(yù)測(cè)變得非常困難�？紤]到比賽的比賽特征之間的相互影響,本文提出了一種基于最大熵原理的NBA賽事勝負(fù)預(yù)測(cè)方法,提高預(yù)測(cè)的正確率。首先,本文考慮到球隊(duì)主力球員的變動(dòng)對(duì)比賽結(jié)果的影響,對(duì)比賽雙方已有的得分進(jìn)行修改;將Page Rank算法的思想運(yùn)用到修改后的歷史比分?jǐn)?shù)據(jù)中,構(gòu)造球隊(duì)之間的投票矩陣;然后利用冪法對(duì)投票矩陣進(jìn)行求解,得到量化球隊(duì)的真實(shí)相對(duì)實(shí)力值。其次,利用K-means聚類算法對(duì)所選取的代表比賽屬性的特征數(shù)據(jù)進(jìn)行離散化處理;并根據(jù)最大熵原理構(gòu)造符合特征的NBAME模型。然后,在訓(xùn)練樣本集上用GIS算法對(duì)NBAME模型進(jìn)行最優(yōu)化訓(xùn)練,得到模型中的參數(shù)的值,從而建立符合訓(xùn)練樣本數(shù)據(jù)的NBAME模型。最后,將測(cè)試樣本中比賽的特征數(shù)據(jù)代入到NBAME模型,計(jì)算對(duì)應(yīng)比賽的主場(chǎng)球隊(duì)獲勝的概率,利用閾值來(lái)確定比賽的勝負(fù)。實(shí)驗(yàn)表明,當(dāng)閾值取0.5時(shí),模型能夠預(yù)測(cè)所有測(cè)試集上的比賽,并且預(yù)測(cè)正確率最高能夠達(dá)到75.6%;當(dāng)閾值提高到0.7時(shí),模型能夠預(yù)測(cè)的比賽場(chǎng)次減少,但預(yù)測(cè)正確率卻可以達(dá)到84.8%。本文所選取比賽的屬性特征和依據(jù)最大熵原理構(gòu)造出的NBAME模型能夠有效的預(yù)測(cè)NBA比賽的勝負(fù),相比現(xiàn)有的機(jī)器學(xué)習(xí)模型的正確率有所提升。
[Abstract]:NBA, the world's most influential league of top basketball events, has attracted the attention of basketball enthusiasts around the world and has long been sought after by the public. And a lot of random factors make it very difficult to predict the result of the competition. Considering the interaction between the characteristics of the competition, this paper proposes a method for predicting the results of NBA events based on the maximum entropy principle. First of all, considering the influence of the change of the main players on the result of the match, this paper modifies the existing scores of both sides of the game, and applies the idea of Page Rank algorithm to the revised historical score data. The voting matrix between teams is constructed, and then the voting matrix is solved by power method to get the real relative strength of the team. Secondly, the K-means clustering algorithm is used to discretize the selected feature data representing the game attributes. According to the principle of maximum entropy, the NBAME model is constructed. Then, the GIS algorithm is used to optimize the NBAME model on the training sample set, and the values of the parameters in the model are obtained. Finally, the NBAME model is established in accordance with the training sample data. The characteristic data of the match in the test sample is inserted into the NBAME model to calculate the probability of the home team winning the corresponding match, and the threshold value is used to determine the winning or losing of the match. The experiment shows that when the threshold is 0.5, The model can predict the matches on all test sets, and the prediction accuracy can reach 75.60.When the threshold is raised to 0.7, the number of matches predicted by the model decreases. However, the prediction accuracy can reach 84.8%. The NBAME model constructed according to the maximum entropy principle and the attribute feature of the selected competition can effectively predict the success or failure of the NBA match, which is improved compared with the existing machine learning model.
【學(xué)位授予單位】：湘潭大學(xué)
【學(xué)位級(jí)別】：碩士
【學(xué)位授予年份】：2017
【分類號(hào)】：G841;TP181

【相似文獻(xiàn)】

相關(guān)期刊論文 前10條

1 王穎哲;;電視轉(zhuǎn)播與體育發(fā)展:以NBA電視轉(zhuǎn)播為例[J];東南傳播;2006年10期

2 光光;;NBA看光光 40分俱樂(lè)部[J];NBA特刊;2010年01期

3 光光;;NBA看光光 明星賽的遺珠之憾[J];NBA特刊;2010年04期

4 光光;;NBA看光光 決戰(zhàn)東西軍[J];NBA特刊;2010年08期

5 ;NBA球星代言球鞋復(fù)古廣告大賞[J];體育世界(扣籃);2011年23期

6 ;NBA全明星扣籃大賽歷年參賽球員球衣[J];當(dāng)代體育;2013年05期

7 ;NBA球星代言球鞋復(fù)古廣告大賞[J];NBA特刊;2013年10期

8 ;2003年夏季NBA各隊(duì)陣容調(diào)整全記錄[J];籃球;2003年10期

9 宋紹斌;NBA技術(shù)圖片選[J];籃球;1995年02期

10 楊昌忠;“NBA”進(jìn)入中國(guó)[J];新體育;1997年02期

相關(guān)會(huì)議論文 前1條

1 杝，

本文編號(hào)：1622711