MétaCan
Menu
Back to cohort
Record W6995687740

Performance of machine learning methods in predicting trend in price and trading volume of cryptocurrencies

2023· dissertation· en· W6995687740 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

VenueSpectrum Research Repository (Concordia University) · 2023
Typedissertation
Languageen
FieldDecision Sciences
TopicStock Market Forecasting Methods
Canadian institutionsConcordia University
Fundersnot available
KeywordsCryptocurrencyLogistic regressionVolume (thermodynamics)Naive Bayes classifierInvestment (military)Support vector machineWork (physics)Regression
DOInot available

Abstract

fetched live from OpenAlex

This study is motivated by the growing interest in cryptocurrency trading and the need for accurate forecasting tools to guide investment decisions. The main aim is to forecast price and trading volume changes of cryptocurrencies by determining their movement directions. Naïve Bayes, support vector machines, logistic regression, regression trees, and the K-nearest neighbors’ algorithm are selected to solve the problem and compared. Performance measures such as accuracy, sensitivity, and specificity are used to assess the models. The study shows that some models are better at predicting volume trends than price trends in cryptocurrencies. Naïve Bayes is good at spotting positive trends, while Logistic Regression is accurate at identifying negative trends. Interestingly, the research reveals that shorter prediction times are more accurate for price forecasts, but intermediate times work better for specificity. These insights help us understand which models work well for different aspects of cryptocurrency forecasting.

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)0.017
metaresearch head score (Gemma)0.010
Version: codex-gemma-dda1882f352aValidation status: machine_predicted_unvalidated
Candidate categoriesMetaresearch, Meta-epidemiology (narrow)
Consensus categoriesnone
DomainCandidate signal: none · Consensus signal: none
Study designCandidate signal: Observational · Consensus signal: Observational
GenreCandidate signal: Empirical · Consensus signal: Empirical
Teacher disagreement score0.058
Threshold uncertainty score1.000

Codex and Gemma teacher scores by category

CategoryCodexGemma
Metaresearch0.0170.010
Meta-epidemiology (narrow)0.0000.000
Meta-epidemiology (broad)0.0010.000
Bibliometrics0.0070.007
Science and technology studies0.0000.000
Scholarly communication0.0000.000
Open science0.0010.000
Research integrity0.0000.002
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 head0.106
GPT teacher head0.408
Teacher spread0.302 · 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