The good, the better and the challenging: Insights into predicting high-growth firms using machine learning
This study aims to classify high-growth firms using several machine learning algorithms, including K-Nearest Neighbors, Logistic Regression with L1 (Lasso) and L2 (Ridge) Regularization, XGBoost, Gradient Descent, Naive Bayes and Random Forest. Leveraging a dataset composed of financial metrics and...
Saved in:
| Main Authors: | , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Elsevier
2024-12-01
|
| Series: | Borsa Istanbul Review |
| Subjects: | |
| Online Access: | http://www.sciencedirect.com/science/article/pii/S2214845024001558 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1832591747973120000 |
|---|---|
| author | Sermet Pekin Aykut Şengül |
| author_facet | Sermet Pekin Aykut Şengül |
| author_sort | Sermet Pekin |
| collection | DOAJ |
| description | This study aims to classify high-growth firms using several machine learning algorithms, including K-Nearest Neighbors, Logistic Regression with L1 (Lasso) and L2 (Ridge) Regularization, XGBoost, Gradient Descent, Naive Bayes and Random Forest. Leveraging a dataset composed of financial metrics and firm characteristics between 2009 and 2022 with 1,318,799 unique firms (averaging 554,178 annually), we evaluate the performance of each model using metrics such as MCC, ROC AUC, accuracy, precision, recall and F1-score. In our study, ROC AUC values ranged from 0.53 to 0.87 for employee-high growth and from 0.53 to 0.91 for turnover-high growth, depending on the method used. Our findings indicate that XGBoost achieves the highest performance, followed by Random Forest and Logistic Regression, demonstrating their effectiveness in distinguishing between high-growth and non-high-growth firms. Conversely, KNN and Naive Bayes yield lower accuracy. Furthermore, our findings reveal that growth opportunity emerges as the most significant factor in our study. This research contributes valuable insights to financial analysts and investors in identifying high-growth firms and underscores the potential of machine learning in economic prediction. |
| format | Article |
| id | doaj-art-11f792fbfb3a44a389cc72961fed34cf |
| institution | Kabale University |
| issn | 2214-8450 |
| language | English |
| publishDate | 2024-12-01 |
| publisher | Elsevier |
| record_format | Article |
| series | Borsa Istanbul Review |
| spelling | doaj-art-11f792fbfb3a44a389cc72961fed34cf2025-01-22T05:42:31ZengElsevierBorsa Istanbul Review2214-84502024-12-01244760The good, the better and the challenging: Insights into predicting high-growth firms using machine learningSermet Pekin0Aykut Şengül1Corresponding author.; Central Bank of the Republic of Türkiye, Research and Monetary Policy Department, TürkiyeCentral Bank of the Republic of Türkiye, Research and Monetary Policy Department, TürkiyeThis study aims to classify high-growth firms using several machine learning algorithms, including K-Nearest Neighbors, Logistic Regression with L1 (Lasso) and L2 (Ridge) Regularization, XGBoost, Gradient Descent, Naive Bayes and Random Forest. Leveraging a dataset composed of financial metrics and firm characteristics between 2009 and 2022 with 1,318,799 unique firms (averaging 554,178 annually), we evaluate the performance of each model using metrics such as MCC, ROC AUC, accuracy, precision, recall and F1-score. In our study, ROC AUC values ranged from 0.53 to 0.87 for employee-high growth and from 0.53 to 0.91 for turnover-high growth, depending on the method used. Our findings indicate that XGBoost achieves the highest performance, followed by Random Forest and Logistic Regression, demonstrating their effectiveness in distinguishing between high-growth and non-high-growth firms. Conversely, KNN and Naive Bayes yield lower accuracy. Furthermore, our findings reveal that growth opportunity emerges as the most significant factor in our study. This research contributes valuable insights to financial analysts and investors in identifying high-growth firms and underscores the potential of machine learning in economic prediction.http://www.sciencedirect.com/science/article/pii/S2214845024001558C40C55C60C81L25 |
| spellingShingle | Sermet Pekin Aykut Şengül The good, the better and the challenging: Insights into predicting high-growth firms using machine learning Borsa Istanbul Review C40 C55 C60 C81 L25 |
| title | The good, the better and the challenging: Insights into predicting high-growth firms using machine learning |
| title_full | The good, the better and the challenging: Insights into predicting high-growth firms using machine learning |
| title_fullStr | The good, the better and the challenging: Insights into predicting high-growth firms using machine learning |
| title_full_unstemmed | The good, the better and the challenging: Insights into predicting high-growth firms using machine learning |
| title_short | The good, the better and the challenging: Insights into predicting high-growth firms using machine learning |
| title_sort | good the better and the challenging insights into predicting high growth firms using machine learning |
| topic | C40 C55 C60 C81 L25 |
| url | http://www.sciencedirect.com/science/article/pii/S2214845024001558 |
| work_keys_str_mv | AT sermetpekin thegoodthebetterandthechallenginginsightsintopredictinghighgrowthfirmsusingmachinelearning AT aykutsengul thegoodthebetterandthechallenginginsightsintopredictinghighgrowthfirmsusingmachinelearning AT sermetpekin goodthebetterandthechallenginginsightsintopredictinghighgrowthfirmsusingmachinelearning AT aykutsengul goodthebetterandthechallenginginsightsintopredictinghighgrowthfirmsusingmachinelearning |