In the dynamic realm of business, effective inventory management plays a pivotal role in the success of organizations. This study explores the feasibility of applying ma- chine learning (ML) models in predicting inventory funding needs through a case study at Polestar, a leading electrical vehicle (EV) brand. Adopting an inductive approach with an exploratory sequential design, the research commences with qualitative data acquisi- tion followed by quantitative analysis. Six individuals at Polestar, whose responsibilities are intertwined with forecasting inventory funding needs, participated in qualitative inter- views. Subsequently, insights from these interviews informed the quantitative phase, where data sourced from Polestar was employed in ARIMA (AutoRegressive Integrated Moving Average), RFR (Random Forest Regression), and XGBoost (Extreme Gradient Boosting) algorithms—identified through literature review as top performers in analogous contexts. Notably, XGBoost exhibited superior performance in terms of Mean Absolute Percentage Error (MAPE), while RFR boasted the highest accuracy rate in predicting actual funding requirements, a point elaborated upon in the following analysis. Anticipating future im- plementation of ML, the study outlines key considerations for focus and further research based on findings from both the qualitative and quantitative study.