Conservative Thirty Calendar Day Stock Prediction Using a Probabilistic Neural Network

H. Tan; Donald C. Wunsch; Danil V. Prokhorov

doi:10.1109/CIFER.1995.495262

Conservative Thirty Calendar Day Stock Prediction Using a Probabilistic Neural Network

H. Tan
, Donald C. Wunsch
, Danil V. Prokhorov

Research output: Contribution to journal › Article › peer-review

Abstract

We describe a system that predicts significant short-term price movement in a single stock utilizing conservative strategies. We use preprocessing techniques, then train a probabilistic neural network to predict only price gains large enough to create a significant profit opportunity. Our primary objective is to limit false predictions (known in the pattern recognition literature as false alarms). False alarms are more significant than missed opportunities, because false alarms acted upon lead to losses. We can achieve false alarm rates as low as 5.7% with the correct system design and parameterization.

Original language	American English
Journal	Proceedings of the IEEE/IAFE 1995 Computational Intelligence for Financial Engineering, 1995
DOIs	https://doi.org/10.1109/CIFER.1995.495262
State	Published - Jan 1 1995

Keywords

30 Day
30-Day Stock Prediction
Conservative Strategies
False Alarms
False Predictions
Financial Data Processing
Forecasting Theory
Losses
Missed Opportunities
Neural Nets
Parameterization
Pattern Recognition
Preprocessing Techniques
Price Gains
Probabilistic Neural Network
Profit Opportunity
Short-Term Price Movement Prediction
Stock Markets
System Design
Uncertainty Handling

Disciplines

Electrical and Computer Engineering

Access to Document

10.1109/CIFER.1995.495262License: Unspecified

Conservative Thirty Calendar Day Stock Prediction Using a ProbabiFinal published version, 348 KBLicense: Unspecified

Cite this

@article{237edb5c831a433594021eb28f62c8f9,

title = "Conservative Thirty Calendar Day Stock Prediction Using a Probabilistic Neural Network",

abstract = " We describe a system that predicts significant short-term price movement in a single stock utilizing conservative strategies. We use preprocessing techniques, then train a probabilistic neural network to predict only price gains large enough to create a significant profit opportunity. Our primary objective is to limit false predictions (known in the pattern recognition literature as false alarms). False alarms are more significant than missed opportunities, because false alarms acted upon lead to losses. We can achieve false alarm rates as low as 5.7\% with the correct system design and parameterization.",

keywords = "30 Day, 30-Day Stock Prediction, Conservative Strategies, False Alarms, False Predictions, Financial Data Processing, Forecasting Theory, Losses, Missed Opportunities, Neural Nets, Parameterization, Pattern Recognition, Preprocessing Techniques, Price Gains, Probabilistic Neural Network, Profit Opportunity, Short-Term Price Movement Prediction, Stock Markets, System Design, Uncertainty Handling",

author = "H. Tan and Wunsch, \{Donald C.\} and Prokhorov, \{Danil V.\}",

year = "1995",

month = jan,

day = "1",

doi = "10.1109/CIFER.1995.495262",

language = "American English",

journal = "Proceedings of the IEEE/IAFE 1995 Computational Intelligence for Financial Engineering, 1995",

}

TY - JOUR

T1 - Conservative Thirty Calendar Day Stock Prediction Using a Probabilistic Neural Network

AU - Tan, H.

AU - Wunsch, Donald C.

AU - Prokhorov, Danil V.

PY - 1995/1/1

Y1 - 1995/1/1

N2 - We describe a system that predicts significant short-term price movement in a single stock utilizing conservative strategies. We use preprocessing techniques, then train a probabilistic neural network to predict only price gains large enough to create a significant profit opportunity. Our primary objective is to limit false predictions (known in the pattern recognition literature as false alarms). False alarms are more significant than missed opportunities, because false alarms acted upon lead to losses. We can achieve false alarm rates as low as 5.7% with the correct system design and parameterization.

AB - We describe a system that predicts significant short-term price movement in a single stock utilizing conservative strategies. We use preprocessing techniques, then train a probabilistic neural network to predict only price gains large enough to create a significant profit opportunity. Our primary objective is to limit false predictions (known in the pattern recognition literature as false alarms). False alarms are more significant than missed opportunities, because false alarms acted upon lead to losses. We can achieve false alarm rates as low as 5.7% with the correct system design and parameterization.

KW - 30 Day

KW - 30-Day Stock Prediction

KW - Conservative Strategies

KW - False Alarms

KW - False Predictions

KW - Financial Data Processing

KW - Forecasting Theory

KW - Losses

KW - Missed Opportunities

KW - Neural Nets

KW - Parameterization

KW - Pattern Recognition

KW - Preprocessing Techniques

KW - Price Gains

KW - Probabilistic Neural Network

KW - Profit Opportunity

KW - Short-Term Price Movement Prediction

KW - Stock Markets

KW - System Design

KW - Uncertainty Handling

UR - https://scholarsmine.mst.edu/ele_comeng_facwork/938

U2 - 10.1109/CIFER.1995.495262

DO - 10.1109/CIFER.1995.495262

M3 - Article

JO - Proceedings of the IEEE/IAFE 1995 Computational Intelligence for Financial Engineering, 1995

JF - Proceedings of the IEEE/IAFE 1995 Computational Intelligence for Financial Engineering, 1995

ER -

Conservative Thirty Calendar Day Stock Prediction Using a Probabilistic Neural Network

Abstract

Keywords

Disciplines

Access to Document

Other files and links

Fingerprint

Cite this