Modelling the financial performance of construction companies using neural network via genetic algorithm
Why this work is in the frame
A frame that forgets how it found something cannot be audited. These are the routes that admitted this work.
Bibliographic record
Abstract
Net profit, annual work volume, and working capital can be considered as the main financial performance indicators for any construction company. Sufficient liquidity must be properly assessed to ensure the survival of the business in both short-term and long-term bases. Large amount of working capital simply means idle funds in a form of current assets that does not gain any profit for the company. On other hand, small amount of working capital means that the company is unable to meet its liabilities and it faces complexity to participate in new project tenders, as a consequence its annual work volume might be decreased. Then, the excess or shortage of working capital affects badly the companies’ profitability. Hence, it is obvious that the construction companies’ working capital, net profit, and annual work volume constitute three interrelated financial performance indicators that have to be appropriately assessed. The present study aims to develop a model to help the construction companies’ managers to assess and forecast their companies’ financial performance indicators: working capital, net profit, and annual work volume. Through this research, the genetic algorithm technique (GA) will be integrated with the neural network technique (NN) to develop the proposed model. The developed model will be able to predict the three financial performance indicators: working capital, net profit, and annual work volume, for an upcoming year based on previously published financial statements data. A comprehensive literature review was conducted and 23 factors were identified as the most influencing factors on the construction companies’ financial indicators: working capital, net profit, and annual work volume. One hundred and sixty four Egyptian construction companies’ financial statements were gathered and analyzed to extract data regarding the identified 23 factors. The extracted data were used to develop a NN–GA hybrid and NN only models to assess the construction companies’ financial indicators. The two developed model outputs are compared to evaluate their predictive capability. This comparison showed that, the NN–GA hybrid model predictive capability is better than the NN only model predictive capability. Incorporating the GA enhances the predicting capability of the developed model by an average of 4.0%.
Fetched live from OpenAlex and de-inverted. Abstracts are not stored in this database: the inverted indexes are 8.6 GB of the frame’s 9.3 GB of text, and the host has 13 GB free.
Full frame distilled prediction
Teacher imitationNot calibrated prevalence, not ground truth. Human validation pending. Learned from the 10,348 direct Codex labels and 10,348 direct Gemma labels. Candidate is the union of thresholded teacher heads; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels or direct frontier model labels.
Codex and Gemma teacher scores by category
| Category | Codex | Gemma |
|---|---|---|
| Metaresearch | 0.000 | 0.000 |
| Meta-epidemiology (narrow) | 0.000 | 0.000 |
| Meta-epidemiology (broad) | 0.000 | 0.000 |
| Bibliometrics | 0.000 | 0.000 |
| Science and technology studies | 0.000 | 0.000 |
| Scholarly communication | 0.000 | 0.000 |
| Open science | 0.000 | 0.000 |
| Research integrity | 0.000 | 0.000 |
| Insufficient payload (model declined to judge) | 0.000 | 0.000 |
Machine scores (provisional)
The two teacher heads of the student model, read on this work. A score orders the frame for review; it never asserts a category, and the validation status ships verbatim with every row.
Baseline scores from an immature model (maturity gate not passed, 7 training rounds). Scores rank; they never assert a category.
score_only:v0-immature-baseline · verbatim from the scoring run: score_only means the number may rank works, and no category label ships from it