Method for predicting stock values using long-short term memory (LSTM) Neural Network algorithm by utilizes deep learning models, involves training LSTM model on the training dataset, and evaluating model performance using testing dataset once training is complete
	ETHIRAJULU V; NELAKURTHY V P; NELAKURTHI N; MAHESH P; KALYAN P P; USHA T
	2023-10-16
专利权人	BHARATH HIGHER EDUCATION & RES INST (BHAR-Non-standard)
申请日期	2023-10-16
专利号	IN202341069430-A
成果简介	NOVELTY - The method involves gathering historical stock price data for the specific stock to predict. The data usually includes the stock opening price, closing price, highest price, lowest price and trading volume for each trading day. The LSTM model is constructed by defining the number of LSTM layers, the number of hidden units in each layer, and the activation functions to be used. The LSTM model is trained on the training dataset. The model learns to recognize patterns and dependencies in the historical stock price data during training. The training process involves forward propagation, backpropagation, and weight updates to minimize the prediction error. The model performance is evaluated using the testing dataset once the training is complete. The common evaluation metrics for stock prediction include mean squared error (MSE), root mean squared error (RMSE), and mean absolute error (MAE). The metrics assess the accuracy of the model predictions compared to the actual stock prices. USE - Method for predicting stock values using long-short term memory (LSTM) Neural Network algorithm by utilizes deep learning models. ADVANTAGE - The method solves the problem of stock prices prediction by utilizing deep learning models, improves the LSTM model accuracy and reduces noise. The training process involves forward propagation, backpropagation, and weight updates to minimize the prediction error.
IPC 分类号	G06K-009/62 ; G06N-020/00 ; G06N-020/20 ; G06N-005/00 ; G06N-007/00
国家	印度
专业领域	信息技术
语种	英语
成果类型	专利
文献类型	科技成果
条目标识符	http://119.78.100.226:8889/handle/3KE4DYBR/19906
专题	中国科学院新疆生态与地理研究所
作者单位	BHARATH HIGHER EDUCATION & RES INST (BHAR-Non-standard)
推荐引用方式 GB/T 7714	ETHIRAJULU V,NELAKURTHY V P,NELAKURTHI N,et al. Method for predicting stock values using long-short term memory (LSTM) Neural Network algorithm by utilizes deep learning models, involves training LSTM model on the training dataset, and evaluating model performance using testing dataset once training is complete. IN202341069430-A[P]. 2023.

条目包含的文件
条目无相关文件。

除非特别说明，本系统中所有内容都受版权保护，并保留所有权利。