Neural network techniques for financial performance prediction: integrating fundamental and technical analysis
Neural network techniques for financial performance prediction: integrating fundamental and technical analysis
复制标题
DOI：
10.1016/s0167-9236(03)00088-5
复制
发表时间：
2004-09-01
影响因子：
7.5
通讯作者：
Lam, M
中科院分区：
文献类型：
--
作者：
Lam, M
本研究项目探讨神经网络的能力，特别是反向传播算法，整合基本面和技术分析的财务业绩预测。预测属性包括16个财务报表变量和11个宏观经济变量。以普通股股东权益收益率作为预测变量。从CompuStat数据库中提取了364家标准普尔公司的财务数据，从Citibase数据库中提取了1985-1995年研究期间的宏观经济变量。在实验1、2和3中，分别使用1年、2年和3年的财务数据作为预测变量。实验4以3年的金融数据和宏观经济数据作为预测变量。此外，为了补偿数据噪声和参数误设定以及揭示预测逻辑和过程，我们采用了规则提取技术，从训练的神经网络的连接权重转换为符号分类规则。神经网络的性能与市场上前三分之一回报的平均回报（最大基准）进行比较，近似于完美信息的回报，以及与整体市场平均回报（最小基准）近似于高度多样化投资组合的回报。进行配对t检验以计算平均差异的统计学显著性。实验结果表明，神经网络使用一年或多年的财务数据一致和显着优于最低基准，但不是最大的基准。至于同时具有金融和宏观经济预测因子的神经网络，它们在本研究中的表现并不优于最小或最大基准。实验结果还表明，从提取的规则的平均回报率为0.25398是唯一兼容的结果，以最大的基准0.2786。因此，我们展示了规则提取作为一种后处理技术，用于提高预测精度和向财务决策者解释预测逻辑。(C)2003 Elsevier B. V.保留所有权利。
This research project investigates the ability of neural networks, specifically, the backpropagation algorithm, to integrate fundamental and technical analysis for financial performance prediction. The predictor attributes include 16 financial statement variables and 11 macroeconomic variables. The rate of return on common shareholders' equity is used as the to-be-predicted variable. Financial data of 364 S&P companies are extracted from the CompuStat database, and macroeconomic variables are extracted from the Citibase database for the study period of 1985-1995. Used as predictors in Experiments 1, 2, and 3 are the 1 year's, the 2 years', and the 3 years' financial data, respectively. Experiment 4 has 3 years' financial data and macroeconomic data as predictors. Moreover, in order to compensate for data noise and parameter misspecification as well as to reveal prediction logic and procedure, we apply a rule extraction technique to convert the connection weights from trained neural networks to symbolic classification rules. The performance of neural networks is compared with the average return from the top one-third returns in the market (maximum benchmark) that approximates the return from perfect information as well as with the overall market average return (minimum benchmark) that approximates the return from highly diversified portfolios. Paired t tests are carried out to calculate the statistical significance of mean differences. Experimental results indicate that neural networks using I year's or multiple years' financial data consistently and significantly outperform the minimum benchmark, but not the maximum benchmark. As for neural networks with both financial and macroeconomic predictors, they do not outperform the minimum or maximum benchmark in this study. The experimental results also show that the average return of 0.25398 from extracted rules is the only compatible result to the maximum benchmark of 0.2786. Consequentially, we demonstrate rule extraction as a postprocessing technique for improving prediction accuracy and for explaining the prediction logic to financial decision makers. (C) 2003 Elsevier B.V. All rights reserved.