Research on Model Decision-making Method Based on ARIMA and LSTM Sequence Analysis
0
Citation
2
Reference
10
Related Paper
Abstract:
For the market model, this paper first uses the ARIMA time series model to analyze why the ARIMA model can predict the time series of gold price changes. After retesting the model, we use the model to predict the value and growth of gold. Then the LSTM neural network is used to effectively avoid the big error caused by the significant deviation in individual cases. It can accurately predict bitcoin quotations through subtle control of memory gates, forgetting gates, and output doors in LSTM. This model is also suitable for the accuracy test of the LSTM model based on MSE, MAE, and other parameters.Keywords:
Sequence (biology)
Value (mathematics)
ARIMA model is widely-range used in forecasting analysis area. The paper establishes an ARIMA model on the employment information of computer industry from 2002 to 2007 in China, and using the model, gives a prediction of situation in 2008. The study will be an exploration for subsequent researches on employment situation forecasting, or other related work.
Technology forecasting
Cite
Citations (14)
Time series forecasting is a machine learning approach providing forecasts by using historical data for analyzing different trends. It involves the direct application of the continuity principle by analyzing the historical pattern of the variable and assuming that the variable will remain constant in the future. This article explores computational models for time series analysis of three commonly used grains (wheat, rice, and maize). The forecast for the next year is made using the autoregressive integrated moving average (ARIMA) based on the previous year's production. ARIMA was fitted after the stationarity of the data variables was determined by the ADF test. The PACF chart is used to discover the best features or parts of the AR process and the next ACF chart is used to find the best features or parts of the MA process. An ARIMA model was developed to determine the yield data for wheat, rice and maize and to predict the forecast for the next five years.The results show that the ARIMA model fits the data with the smallest root mean square error (RMSE).
Box–Jenkins
Moving average
Cite
Citations (3)
Time series data analysis is a method of predicting future values by observing historical data and exploring its random laws. The satellite's on-orbit operation generates a large amount of telemetry variable time series data. Satellite system state prediction with generated data plays an important role in satellite health management. However, the traditional Autoregressive Integrated Moving Average model (ARIMA) for prediction has difficulties in high precision prediction with complex inputs. Towards this aim, we propose the LSTM-ARIMA algorithm to predict the time series data of a meteorological satellite telemetry parameter and analyze the error of the prediction data. Long Short Term Memory (LSTM) neural network is more flexible than ARIMA algorithm and has room for optimization. By combining the two algorithm models by weight, LSTM-ARIMA algorithm yields high accuracy and strong reliability prediction results and mines the loss rule of the satellite telemetry parameters.
Cite
Citations (20)
Time series forecasting using historical data is significantly important nowadays. Many fields such as finance, industries, healthcare, and meteorology use it. Profit analysis using financial data is crucial for any online or offline businesses and companies. It helps understand the sales and the profits and losses made and predict values for the future. For this effective analysis, the statistical methods- Autoregressive Integrated Moving Average (ARIMA) and Seasonal ARIMA models (SARIMA), and deep learning method- Long Short- Term Memory (LSTM) Neural Network model in time series forecasting have been chosen. It has been converted into a stationary dataset for ARIMA, not for SARIMA and LSTM. The fitted models have been built and used to predict profit on test data. After obtaining good accuracies of 93.84% (ARIMA), 94.378% (SARIMA) and 97.01% (LSTM) approximately, forecasts for the next 5 years have been done. Results show that LSTM surpasses both the statistical models in constructing the best model.
Moving average
Cite
Citations (72)
Time series analysis and forecasting has become a major tool in different applications in meteorological phenomena such as rainfall, humidity, temperature, draught and so on; and environmental fields. Among the most effective approaches for analyzing time series data is the ARIMA (Autoregressive Integrated Moving Average) model introduced by Box and Jenkins. In this study, Box-Jenkins methodology was used to model monthly rainfall data taken from Maiduguri Airport Station for the period from 1981 to 2011 with a total of 372 readings. ARIMA (1, 1,0) model was developed. This model was used to forecast monthly rainfall for the upcoming 44 months (3 years 8 months) to help decision makers establish priorities in terms of water demand management and agriculture. Thus, ARIMA (1, 1,0) provides a good fit for the rainfall data of Maiduguri and is appropriate for short term forecast.Key Words: Time Series Analysis, Rainfall Model, Forecasting, ARIMA.
Box–Jenkins
Moving average
Cite
Citations (4)
ARIMAmodel is a kind of time series prediction model which possesses high precision.Based on the econometrics software Eviwes5.0 and total social investment in fixed assets data of Jilin Province in 1980-2005,the economic model ARIMA(3,1,2) is established to perform the prediction analysis on the total social investment in fixed assets of Jilin Province in the future.It is a good solution to the modeling for non-stationary time series.
Investment
Cite
Citations (5)
In most of the developed nations, there are markets where shares, securities or commodities are traded on daily basis, which generally reflects the growth of any country and the health of the company stocks which are traded.Stock market investment is considered to be one of the riskiest investments by investors all around the world, but if historical data is studied carefully then the gap between how the market behaves and what investors know, can be minimized.The data of opening and closing price, which is generated, is a times-series in nature. This time-series data of any index or stock attracts researchers to predict the next move or price of the commodity or index.There are lots of methods available to analyze the data like auto-regressive integrated moving average (ARIMA), regression based, neural network or moving averages methods.However, ARIMA is a type of model which is generally applied to the time-series data to gain insights into data,to understand what happened in the past and what is the next move to expect. In this chapter, an attempt has been made to use the time-series data of the past 5 years and based on that we can forecast the future direction of the indices.
Moving average
Commodity market
Cite
Citations (0)
Machine learning time series models have been used to predict COVID-19 pandemic infections. Based on the public dataset from Johns Hopkins, we present a novel framework for forecasting COVID-19 infections. We implement our framework for the United Arab Emirates (UAE) and develop autoregressive integrated moving average (ARIMA) time series forecast model. To the best of our knowledge, this is the only study to forecast the infections in UAE using the time series model.
Pandemic
2019-20 coronavirus outbreak
Cite
Citations (7)
Forecasting time series data is an important subject in economics and business where the Autoregressive Integrated Moving Average (ARIMA) has been extensively used despite its weaknesses, from requiring a minimum number of data points to the assumed linearity of data. With recent advancement, the Long Short-Term Memory (LSTM) shows potential to address such weaknesses. This research is aimed to identify a more suitable model in handling irregular data. Performance metrics used are the model accuracy measured with RMSE and the model run-time performance measured with the Python Timeit library. This research concluded that LSTM is more accurate than ARIMA (RMSE of ARIMA 0.144887 to LSTM 0.051828) in a shorter dataset of 36 data points and this result is reverted in longer dataset of 228 data points (RMSE of ARIMA 0.006949 to LSTM 0.036025). In terms of run-time performance, ARIMA is significantly faster than LSTM while the LSTM modelling time is increasing proportionally to the number of the training data points.
Data point
Python
Cite
Citations (5)
Time series prediction is incredibly important and difficult; external factors can also affect prediction results. Therefore, this study compares the following two models to see which makes better predictions. The traditional model is the "Autoregressive Integrated Moving Average" (ARIMA). Over time, new variables like SRIMA (seasonal ARIMA) have emerged. This model is better for short-term prediction than long-term prediction. Another model, CNN and RNN, is more dependent on artificial intelligence data analysis and closer to upcoming technologies. This research focuses on LSTM neural networks, which can learn from historical data and relate to present data. According to this paper's data, LSTM's data prediction is superior to the ARIMA model.
Cite
Citations (0)