Predicting Patent Transactions Using Patent-Based Machine Learning Techniques

Predicting Patent Transactions Using Patent-Based Machine Learning Techniques

Technology transfer becomes imperative in recent business environment where technology changes rapidly and its complexity becomes sophisticated. Among various context of technology transfer, it is especially important to predict patent transactions in such fast-changing industries. Therefore, this s...

Full description

Bibliographic Details
Main Authors: Mirae Kim, Youngjung Geum
Format: Article
Language:English
Published: IEEE 2020-01-01
Series:IEEE Access
Subjects:
Technology transfer
patent transaction
patent assignment
patent
machine learning
Online Access:https://ieeexplore.ieee.org/document/9223646/
id doaj-4bc0684e63d6484382c8e325363213fc
record_format Article
spelling doaj-4bc0684e63d6484382c8e325363213fc2021-03-30T03:26:15ZengIEEEIEEE Access2169-35362020-01-01818883318884310.1109/ACCESS.2020.30309609223646Predicting Patent Transactions Using Patent-Based Machine Learning TechniquesMirae Kim0Youngjung Geum1https://orcid.org/0000-0001-7346-2060MSD Korea Ltd., Seoul, South KoreaDepartment of Industrial and Information Systems Engineering, Seoul National University of Science and Technology (SeoulTech), Seoul, South KoreaTechnology transfer becomes imperative in recent business environment where technology changes rapidly and its complexity becomes sophisticated. Among various context of technology transfer, it is especially important to predict patent transactions in such fast-changing industries. Therefore, this study aims to suggest a predictive model for patent transaction considering a wide range of decision variables. For this purpose, this study highlighted two considerations-technological impact of technology donor and technological proximity in previous patent transactions. Six factors are employed for developing our predictive model-technological strength, knowledge accumulation, technological protection scope, technological jurisdiction, technological strength of companies, and previous history of patent transfers. Five machine learning techniques are employed. As a result, we find that technological strength of companies and previous transfer history significantly affect technology transfer. This study is expected to be used in practice where the technology buying decision is very complicated and comprehensive.https://ieeexplore.ieee.org/document/9223646/Technology transferpatent transactionpatent assignmentpatentmachine learning
collection DOAJ
language English
format Article
sources DOAJ
author Mirae Kim
Youngjung Geum
spellingShingle Mirae Kim
Youngjung Geum
Predicting Patent Transactions Using Patent-Based Machine Learning Techniques
IEEE Access
Technology transfer
patent transaction
patent assignment
patent
machine learning
author_facet Mirae Kim
Youngjung Geum
author_sort Mirae Kim
title Predicting Patent Transactions Using Patent-Based Machine Learning Techniques
title_short Predicting Patent Transactions Using Patent-Based Machine Learning Techniques
title_full Predicting Patent Transactions Using Patent-Based Machine Learning Techniques
title_fullStr Predicting Patent Transactions Using Patent-Based Machine Learning Techniques
title_full_unstemmed Predicting Patent Transactions Using Patent-Based Machine Learning Techniques
title_sort predicting patent transactions using patent-based machine learning techniques
publisher IEEE
series IEEE Access
issn 2169-3536
publishDate 2020-01-01
description Technology transfer becomes imperative in recent business environment where technology changes rapidly and its complexity becomes sophisticated. Among various context of technology transfer, it is especially important to predict patent transactions in such fast-changing industries. Therefore, this study aims to suggest a predictive model for patent transaction considering a wide range of decision variables. For this purpose, this study highlighted two considerations-technological impact of technology donor and technological proximity in previous patent transactions. Six factors are employed for developing our predictive model-technological strength, knowledge accumulation, technological protection scope, technological jurisdiction, technological strength of companies, and previous history of patent transfers. Five machine learning techniques are employed. As a result, we find that technological strength of companies and previous transfer history significantly affect technology transfer. This study is expected to be used in practice where the technology buying decision is very complicated and comprehensive.
topic Technology transfer
patent transaction
patent assignment
patent
machine learning
url https://ieeexplore.ieee.org/document/9223646/
work_keys_str_mv AT miraekim predictingpatenttransactionsusingpatentbasedmachinelearningtechniques
AT youngjunggeum predictingpatenttransactionsusingpatentbasedmachinelearningtechniques
_version_ 1724183399000702976

Similar Items