MétaCan
Menu
Back to cohort
Record W4285677531 · doi:10.1155/2022/4514300

Financial Stock Investment Management Using Deep Learning Algorithm in the Internet of Things

2022· article· en· W4285677531 on OpenAlex

Why this work is in the frame

A frame that forgets how it found something cannot be audited. These are the routes that admitted this work.

affAt least one author lists a Canadian institution in the pinned OpenAlex snapshot.

Bibliographic record

VenueComputational Intelligence and Neuroscience · 2022
Typearticle
Languageen
FieldDecision Sciences
TopicStock Market Forecasting Methods
Canadian institutionsUniversity of Toronto
Fundersnot available
KeywordsComputer scienceArtificial neural networkArtificial intelligenceDatabase transactionStock marketAlgorithmStock (firearms)Machine learningFinanceEconomicsDatabase

Abstract

fetched live from OpenAlex

This paper aims to explore a new model to study financial stock investment management (SIM) and obtain excess returns. Consequently, it proposes a financial SIM model using deep Q network (DQN) as reinforcement earning (RL) algorithm and Long Short-Term Memory (LSTM) as deep neural network (DNN). Then, after training and optimization, the proposed model is back-tested. The research findings are as follows: the LSTM neural network (NN)-based model will import the observation of the market at each time and the change of transaction information over time. The LSTM network can find and learn the potential relationship between time series data. There are two hidden layers and one output layer in the model. The hidden layer is an LSTM structure and the output layer is the fully connected NN. DQN algorithm first stores the experience sample data of the agent-environment interaction into the experience pool. It then randomly selects a small batch of data from the experience pool to train the network. Doing so removes the correlation and dependence between samples so that the DNN model can better learn the value function in the RL task. The model can predict the future state according to historical information and decide which actions to take in the next step. Meanwhile, five stocks of Chinese A-shares are selected to form an asset pool. The initial 500,000 amount of the account is divided into five equal shares, which are invested and traded. Overall, the model account's rate of return (RoR) during the back-test is 32.12%. The Shanghai Stock Exchange (SSI) has risen by 19.157% in the same period. Thus, the model's performance has exceeded the SSI's in the same period. E stock has the maximum RoR of 78.984%. The RoR of A, B, and C stocks is 54.129%, 11.594%, and 9.815%, respectively. B stock presents a minimum RoR of 6.084%. All these stocks have got positive returns. Therefore, the proposed financial SIM based on the DL algorithm is scientific and feasible. The research content has certain significant reference for the DL-based financial SIM.

Fetched live from OpenAlex and de-inverted. Abstracts are not stored in this database: the inverted indexes are 8.6 GB of the frame’s 9.3 GB of text, and the host has 13 GB free.

Full frame distilled prediction

Teacher imitation

Not calibrated prevalence, not ground truth. Human validation pending. Learned from the 10,348 direct Codex labels and 10,348 direct Gemma labels. Candidate is the union of thresholded teacher heads; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels or direct frontier model labels.

metaresearch head score (Codex)0.005
metaresearch head score (Gemma)0.002
Version: codex-gemma-dda1882f352aValidation status: machine_predicted_unvalidated
Candidate categoriesnone
Consensus categoriesnone
DomainCandidate signal: none · Consensus signal: none
Study designCandidate signal: Simulation or modeling · Consensus signal: Simulation or modeling
GenreCandidate signal: Empirical · Consensus signal: none
Teacher disagreement score0.793
Threshold uncertainty score0.314

Codex and Gemma teacher scores by category

CategoryCodexGemma
Metaresearch0.0050.002
Meta-epidemiology (narrow)0.0000.000
Meta-epidemiology (broad)0.0000.000
Bibliometrics0.0000.002
Science and technology studies0.0000.000
Scholarly communication0.0000.000
Open science0.0010.001
Research integrity0.0000.000
Insufficient payload (model declined to judge)0.0000.000

Machine scores (provisional)

The two teacher heads of the student model, read on this work. A score orders the frame for review; it never asserts a category, and the validation status ships verbatim with every row.

Baseline scores from an immature model (maturity gate not passed, 7 training rounds). Scores rank; they never assert a category.

Opus teacher head0.181
GPT teacher head0.404
Teacher spread0.223 · how far apart the two teachers sit on this one work
Validation statusscore_only:v0-immature-baseline · verbatim from the scoring run: score_only means the number may rank works, and no category label ships from it