Forecasting Directional Movement of Stock Prices using Deep Learning

Chandola, Deeksha; Mehta, Akshit; Singh, Shikha; Tikkiwal, Vinay Anand; Agrawal, Himanshu

doi:10.1007/s40745-022-00432-6

Cited by 20 publications

(9 citation statements)

References 25 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…Support Vector Machine sering digunkan untuk membuat prediksi, seperti ramalan jangka panjang [12]. Support Vector Machine mengalami perkembangan yang sangat pesat [12], Support Vector Machine mampu menyelesaikan klasifikasi dan regresi dengan linear ataupun non-linear kernel hyperplane yang menjadikannya algoritma machine learning paling efisien untuk klasifikasi [13].…”

Section: Support Vector Machineunclassified

“…Metode evaluasi Confusion matrix dapat diartikan suatu pengukuran performa terhadap permasalahan klasifikasi machine learning yang mana berupa hasil lebih dari satu kelas [14]. Confusion matrix merupakan tabel penyataan klasifikasi jumlah suatu data uji benar maupun salah [13]. Dalam hasil proses klasifikasi didalam confusion matrix terbilang empat label berbeda diantaranya, False Negative, True Positive, False Negative, dan True Positive [15], [16].…”

Section: Evaluasiunclassified

See 1 more Smart Citation

Analisis Sentimen Menggunakan Support Vector Machine Masyarakat Indonesia Di Twitter Terkait Bjorka

Maulaya¹,

Junadhi²

2022

CoSciTech

View full text Add to dashboard Cite

Belum lama ini seorang hacker bersamarkan nama bjorka menjadi pembahasan hangat pada media sosial. Dikarenakan gerakannya meretas beraneka macam data pribadi pada kalangan masyarakat sekalipun dokumen pemerintah yang sering sebagai tujuan aksinya. Terlebih sebagian besar dokumen diduga kepemilikan Presiden Indonesia Joko Widodo telah dibongkar. Gerakan hacker bersamarkan nama Bjorka membongkar data pribadi kepemilikan pemerintah juga meraih dukungan dari sebagian besar warga netizen pada media sosial. Pada kasus ini penulis memakai metode Support Vector Machine guna menghasilkan tahapan optimal. Seiring meningkatnya penggunaan Twitter, media sosial yang berkomputasi dengan waktu nyata terhadap masyarakat mampu mengirimkan berbagai ungkapan maupun tanggapannya pada aksi yang dilakukan oleh bjorka, perlu dirancangnya sistem yang sanggup mengklasifikasi sejumlah cuitan berbobotkan opini mengarah pada suatu kelas, tergolong positif, negatif dan netral.

show abstract

Section: Support Vector Machineunclassified

Section: Evaluasiunclassified

Analisis Sentimen Menggunakan Support Vector Machine Masyarakat Indonesia Di Twitter Terkait Bjorka

Maulaya¹,

Junadhi²

2022

CoSciTech

View full text Add to dashboard Cite

show abstract

“…With advances in computer technology and statistical methods, modern stock price prediction models have gradually shifted to data-driven methods based on linear models, random forests, and LSTMs [3]. These models use of large amount of data and advanced algorithms to predict future stock prices with higher accuracy and interpretability [4]. In investment, accurate stock price forecasting can help people formulate more effective investment strategies, optimize asset allocation, and reduce risks.…”

Section: Introductionmentioning

confidence: 99%

“…In order to ensure data quality and consistency, stocks with complete data and no outliers were screened. Meanwhile, in order to comprehensively assess the effect of the model, mean square error (RMSE) is used as evaluation indexes [4]. In the experimental process, three models are used to model, train, and predict the data through Python and related functions and packages, and the prediction results are evaluated to analyze the performance and explore the advantages and disadvantages of each model.…”

Section: Introductionmentioning

confidence: 99%

Comparison of stock price prediction models for linear models, random forest and LSTM

2024

ACE

View full text Add to dashboard Cite

With the rapid development of financial markets, accurate stock price prediction is significant to investors and financial institutions. Many researchers proposed stock price prediction models, including linear models, random forests, and LSTMs. However, few studies have comprehensively compared the three models. This study aims to fill this gap by analysing the forecasting effectiveness of different models through empirical studies. This research is to explore the application of linear models, random forests, and LSTM models in predicting stock prices and analyse and compare the principles, advantages and disadvantages, and the scope of application of these three models. According to the analysis, they all have their scope of application and limitations in different situations. In practical application, the appropriate model can be chosen for prediction and analysis according to the specific data sets and research purpose. Meanwhile, it is also possible to try to integrate and improve different models to get better prediction results. In addition, the influence of data quality and completeness, feature selection and extraction from the prediction results should be noted to improve the prediction accuracy and stability of the model. In conclusion, this thesis provides some references and lessons for related studies and practical applications by analysing and comparing the applications of LSTM, linear models, and random forests in predicting stock prices.

show abstract

“…With complicated nature and high volatility market situation is found to be very hard to predict. A hybrid deep learning model integrating Word2Vec and long short term memory (LSTM) algorithms were designed in [5] with the purpose of forecasting directional stock market price movement on the basis of nancial time series, therefore improving prediction accuracy. Financial fraud has immensely mangled the justi able magni cation of nancial markets as a far-reaching issue globally.…”

Section: Introductionmentioning

confidence: 99%

Box Jenkins Neural Network Keynecian Reinforcement Learning Based Financial Big Data Analysis for Optimal Prediction

Zhang

2022

Preprint

View full text Add to dashboard Cite

In the digital era, Economic and Finance information is huge and attainable. The financial industry is a key to stimulating the evolution of the national economy, and with the immense availability of huge data makes the process of financial data analysis both a time consuming and tedious decision making in the financial market. By analyzing this Economic and Finance information significantly and easily, valuable perceptions can be provided. For rational economic growth, information pertaining to economic affairs and likelihoods is critical to decision-makers like governmental bodies, financial institutions and banks. However, precise predictions have been demand owing to the intricacy and unpredictability of financial and economic systems in the midst of persistent changes in economic environments. This work provides to approaches for better economic prediction and decision-making using a novel method called, Multivariate Box Jenkins Neural Network-based Keynecian Reinforcement Learning (MBJNN-KRL). In this work, Financial Data Analysis Deep Economic Prediction model that contains a Multivariate Box Jenkins Long Short Term Memory Forecasting model, for better economic prediction and convergence speed even in case of large data is first designed. The deep reinforcement learning technique is then adapted to retrain neural networks and rebalance the aggregate expenditure periodically. We combined the multivariate Multivariate Box Jenkins Long Short Term Memory Forecasting and the Keynecian Reinforcement Learning models into a single integrated reinforcement learning model named Multivariate Box Jenkins Neural Network-based Keynecian Reinforcement Learning (MBJNN-KRL). Finally, distinct sets of experiments are carried out on real large-scale data set, and the results entirely prove the efficiency and robustness of the proposed method in arbitrary economic prediction based on financial data. Our empirical data revealed that the MBJNN-KRL method could attain combative financial performance compared to traditional methods in terms of predictive accuracy, convergence speed and prediction error.

show abstract

Forecasting Directional Movement of Stock Prices using Deep Learning

Cited by 20 publications

References 25 publications

Analisis Sentimen Menggunakan Support Vector Machine Masyarakat Indonesia Di Twitter Terkait Bjorka

Analisis Sentimen Menggunakan Support Vector Machine Masyarakat Indonesia Di Twitter Terkait Bjorka

Comparison of stock price prediction models for linear models, random forest and LSTM

Box Jenkins Neural Network Keynecian Reinforcement Learning Based Financial Big Data Analysis for Optimal Prediction

Contact Info

Product

Resources

About