Summary of Design Of Reliable Technology Valuation Model with Calibrated Machine Learning Of Patent Indicators, by Seunghyun Lee et al.
Design of reliable technology valuation model with calibrated machine learning of patent indicators
by Seunghyun Lee, Janghyeok Yoon, Jaewoong Choi
First submitted to arxiv on: 8 Jun 2024
Categories
- Main: Computation and Language (cs.CL)
- Secondary: Artificial Intelligence (cs.AI)
GrooveSquid.com Paper Summaries
GrooveSquid.com’s goal is to make artificial intelligence research accessible by summarizing AI papers in simpler terms. Each summary below covers the same AI paper, written at different levels of difficulty. The medium difficulty and low difficulty versions are original summaries written by GrooveSquid.com, while the high difficulty version is the paper’s original abstract. Feel free to learn from the version that suits you best!
| Summary difficulty | Written by | Summary |
|---|---|---|
| High | Paper authors | High Difficulty Summary Read the original abstract here |
| Medium | GrooveSquid.com (original content) | Medium Difficulty Summary Machine learning has transformed the evaluation of technology patents, allowing for highly accurate predictions of their value. However, experts struggle to trust these predictions due to concerns about model reliability. To address this issue, we propose an analytical framework that uses calibrated machine learning models to provide robust confidence levels in predictions. We develop multiple models and evaluate their reliability and accuracy using metrics like expected calibration error, Matthews correlation coefficient, and F1-scores. The best-performing model is then applied to a case study, demonstrating its practical value for developing reliable technology valuation models. |
| Low | GrooveSquid.com (original content) | Low Difficulty Summary Machine learning has made it possible to accurately predict the value of patents. However, experts don’t trust these predictions because they’re not sure if the models are reliable. To fix this problem, we developed an approach that uses special machine learning models called calibrated models. These models provide a measure of how confident they are in their predictions. We tested different models and found the best one by comparing them using special metrics like accuracy and reliability. The best model was then applied to a real-life example, showing how it can be used in practice. |
Keywords
» Artificial intelligence » Machine learning
