Predicting Clearing Date of Account Receivables with Focus on Total Amount Paid
Identifikátory výsledku
Kód výsledku v IS VaVaI
<a href="https://www.isvavai.cz/riv?ss=detail&h=RIV%2F61989100%3A27510%2F23%3A10254354" target="_blank" >RIV/61989100:27510/23:10254354 - isvavai.cz</a>
Výsledek na webu
<a href="https://www.ekf.vsb.cz/smsis/en/" target="_blank" >https://www.ekf.vsb.cz/smsis/en/</a>
DOI - Digital Object Identifier
—
Alternativní jazyky
Jazyk výsledku
angličtina
Název v původním jazyce
Predicting Clearing Date of Account Receivables with Focus on Total Amount Paid
Popis výsledku v původním jazyce
The ability to predict the inflow and outflow of the money is crucial for many companies across various industries. Because each company has at least some control to choose when it will pay the debts (account payables), the tougher part is to predict the customer's behavior, so to predict when the company will receive the money due (account receivables). This study used 40,000 account receivables from year 2019 to train a Random Forest Regression model and 6,000 invoices from year 2020 to test the performance of the model. Sample weight parameter and also custom scoring function were tested to emphasize invoices based on the amount due. The best model with sample weight parameter was able to predict clearing date with mean absolute error of 3 days. The predictions were also aggregated to get weekly sums of amounts predicted to receive and amounts actually received. With the average percentage difference being 5.5 % it was proven that machine learning is able to accurately support financial experts managing cash flow.
Název v anglickém jazyce
Predicting Clearing Date of Account Receivables with Focus on Total Amount Paid
Popis výsledku anglicky
The ability to predict the inflow and outflow of the money is crucial for many companies across various industries. Because each company has at least some control to choose when it will pay the debts (account payables), the tougher part is to predict the customer's behavior, so to predict when the company will receive the money due (account receivables). This study used 40,000 account receivables from year 2019 to train a Random Forest Regression model and 6,000 invoices from year 2020 to test the performance of the model. Sample weight parameter and also custom scoring function were tested to emphasize invoices based on the amount due. The best model with sample weight parameter was able to predict clearing date with mean absolute error of 3 days. The predictions were also aggregated to get weekly sums of amounts predicted to receive and amounts actually received. With the average percentage difference being 5.5 % it was proven that machine learning is able to accurately support financial experts managing cash flow.
Klasifikace
Druh
D - Stať ve sborníku
CEP obor
—
OECD FORD obor
50200 - Economics and Business
Návaznosti výsledku
Projekt
—
Návaznosti
S - Specificky vyzkum na vysokych skolach
Ostatní
Rok uplatnění
2023
Kód důvěrnosti údajů
S - Úplné a pravdivé údaje o projektu nepodléhají ochraně podle zvláštních právních předpisů
Údaje specifické pro druh výsledku
Název statě ve sborníku
Proceedings of the 15th International Conference on Strategic Management and its Support by Information Systems 2023: May 22-24, 2023, Ostrava, Czech Republic
ISBN
978-80-248-4687-3
ISSN
2570-5776
e-ISSN
2570-5776
Počet stran výsledku
10
Strana od-do
226-235
Název nakladatele
VŠB - Technical University of Ostrava
Místo vydání
Ostrava
Místo konání akce
Ostrava
Datum konání akce
22. 5. 2023
Typ akce podle státní příslušnosti
WRD - Celosvětová akce
Kód UT WoS článku
—