Skip to main content
Advertisement
Browse Subject Areas
?

Click through the PLOS taxonomy to find articles in your field.

For more information about PLOS Subject Areas, click here.

< Back to Article

Table 1.

Comparison with the related studies.

More »

Table 1 Expand

Fig 1.

Framework for marketable value estimation of patents.

[a: The topic allocation probability used as an independent variable of the base-learner is calculated through LDA-based topic modeling. b: The market value of a patent used as a dependent variable is calculated through the event study methodology. c: Random Forest, MLP, and CNN are used as base learners. d: SVR is used as the algorithm of the ensemble model that calculates the final predicted value through the predicted value of the base-learner].

More »

Fig 1 Expand

Fig 2.

Graphical model representation of the LDA model.

[a: K stands for the number of topics. b: M indicates the number of documents. c: N represents the total number of words in the document].

More »

Fig 2 Expand

Table 2.

Model comparison.

More »

Table 2 Expand

Table 3.

Words and their weights for each topic.

More »

Table 3 Expand

Table 4.

Dominant topics for each document and the probability of being included in individual topics.

More »

Table 4 Expand

Fig 3.

Perplexity score results for selecting optimal topics.

[a: Perplexity score by topic. b: Perplexity score increase/decrease rate by topic].

More »

Fig 3 Expand

Fig 4.

Coherence score results for selecting optimal topics.

[a: Coherence score by topic. b: Coherence score increase/decrease rate by topic].

More »

Fig 4 Expand

Table 5.

Feature importance results using random forest.

More »

Table 5 Expand

Fig 5.

Regression results for the stock return and index return for the first eight patents.

[stock name compared to S&P 500 index—a: analog devices, b-c: applied materials, d: northrop grumman, e: life storage, f: tower semiconductor, g: Emerson Electric, h: GE].

More »

Fig 5 Expand

Table 6.

Sample of abnormal return calculation results.

More »

Table 6 Expand

Table 7.

Basic statistics on the calculation results of abnormal returns for each subtechnical field of all patent document.

More »

Table 7 Expand

Table 8.

Hyperparameter tuning result by fold: Random forest.

More »

Table 8 Expand

Table 9.

Hyperparameter tuning result by fold: MLP.

More »

Table 9 Expand

Table 10.

Hyperparameter tuning result by fold: CNN.

More »

Table 10 Expand

Table 11.

Hyperparameter tuning result of meta learner (SVR).

More »

Table 11 Expand

Table 12.

Hyperparameter setting results of ensemble model.

More »

Table 12 Expand

Fig 6.

Changes in the loss rate according to an increase in epochs [a: prediction error of MLP model. b: prediction error of CNN model].

More »

Fig 6 Expand

Table 13.

Hyperparameter tuning result of control group.

More »

Table 13 Expand

Fig 7.

Prediction comparison (horizontal axis: Prediction value, vertical axis: Target value).

[a: Linear regression model predicted value and target value scatterplot, b: Random forest model predicted value and target value scatterplot, c: MLP model predicted value and target value scatterplot, d: CNN model predicted value and target value scatterplot, e: Ensemble model predicted value and target value scatterplot].

More »

Fig 7 Expand

Table 14.

Prediction error results for each model.

More »

Table 14 Expand

Table 15.

Results of normality test (Anderson-Darling normality test).

More »

Table 15 Expand

Table 16.

Results of the Wilcoxon rank-sum test with continuity correction.

More »

Table 16 Expand