<p>Descriptive statistics.</p>

1,271 listed companies from Korea's KOSPI and KOSDAQ markets form a dataset for predicting corporate management performance. The data combines financial variables with strategic indicators derived from text mining CEO messages in sustainability reports, covering the period from 2016 to 2023. Author Xiao Wang published this dataset on figshare in May 2026 under a CC-BY-4.0 license.

Use Cases

• Predict corporate management performance based on combined financial and text-derived strategic variables.
• Benchmark machine learning and deep learning classifiers like Transformer and LSTM on a financial prediction task.
• Analyze the impact of CEO communication themes, categorized via the Sustainable Balanced Scorecard, on company performance.
• Study the predictive power of hybrid models integrating structured financial data with unstructured text data.

Strengths

• Contains data from 1,271 listed companies, providing a substantial sample size.
• Covers an 8-year time range from 2016 to 2023, allowing for temporal analysis.
• Integrates two distinct data types: structured financial variables and text-mined strategic indicators from CEO messages.
• The associated research reports specific model performance metrics, such as an Accuracy of 0.8467 for the best hybrid model.

Limitations

• Column-level documentation is absent; field semantics must be inferred after download.
• Row count is unknown, which may limit suitability assessment for certain modeling tasks.
• The dataset is very small at 9.5 KB, indicating limited scope or highly aggregated descriptive statistics.

Provenance

Source

figshare

Collection Method

Combined financial data with strategic information extracted via text mining from CEO messages in sustainability reports.

Time Range

2016-2023

Freshness

Last updated 2026-05-06 17:32:44; freshness should be verified.

Geography

South Korea (KOSPI and KOSDAQ markets)