Stock price prediction using multiple valuationmethods based on artificial neural networks forKOSDAQ
由dandelion4创建，最终由dandelion4 被浏览 40 用户
摘要
很难预测首次公开募股 (IPO) 的未来收益，因为用于确定 IPO 价格的多重估值方法通过反映特定市场环境中的当前情绪来提供估计。 由于我们的模型反映了会计信息和股票价格，我们发现验证 IPO 股票估值准确性的平均绝对百分比误差将投资回报率提高了 15% 到 20%。 这可以帮助股东和投资者准确估计股价并进行高效的投资决策，同时通过将机器学习应用于传统技术来分析投资机会和优化交易策略，为金融科技做出贡献。
It is difficult to predict future payoffs for initial public offerings (IPOs),since the multiple valuation method used to determine IPOs’pricesprovides estimates by reflecting current sentiments in specific marketenvironments. As our model reflects accounting information and stockprice, wefind that the mean absolute percentage error that verifies theaccuracy of IPO stock valuation improves return on investment by 15%to 20%. This can help shareholders and investors accurately estimatestock prices and engage in efficient investment decision-making, whilecontributing tofintech by applying machine learning to traditionaltechniques to analyse investment opportunities and optimise tradingstrategies.
研究报告
/wiki/static/upload/3b/3ba880c4-fa2f-449f-94dc-bede444b86ee.pdf
\