针对可获取数据的不同情况,分别建立了基于最小二乘支持向量机(LS-SVM)回归和容斥原理的广告媒体组合整体效果计算模型以对媒体间广告复合效果进行处理。前者的目的在于解决现有方法处理小样本数据时泛化能力不足的问题;后者则首次讨论了复合效果数据可获取情况下媒体间广告复合效果如何处理的问题。通过某金融机构的实际数据对建立的模型分别进行了验证。结果表明,两个模型都能较好地处理媒体间广告的复合效果,从而准确地计算出广告媒体组合的整体效果。和现有方法的比较表明,基于LSSVM回归的模型在泛化能力上有了明显的改善。 According to the different situations of the available data, the advertising media combination overall effect computing model based on least square support vector machine (LS-SVM) regression and capacitive exclusion principle is established to deal with the media composite effect. The former aims to solve the problem of insufficient generalization ability of existing methods when dealing with small sample data, and the latter discusses for the first time how to deal with the compound effect of media inter-media when the compound effect data is available. Through the actual data of a financial institution, the established models are verified respectively. The results show that both models can better deal with the compound effect of the advertisement in the media, so as to accurately calculate the overall effect of the advertisement media combination. The comparison with the existing methods shows that the model based on LSSVM regression has obvious improvement in generalization ability.