Over the past two decades, machine learning techniques have been extensively used in predicting reservoir properties. While this approach has significantly contributed to the industry, selecting an appropriate model is still challenging for most researchers. Relying solely on statistical metrics to select the best model for a particular problem may not always be the most effective approach. This study encourages researchers to incorporate data visualization in their analysis and model selection process. To evaluate the suitability of different models in predicting horizontal permeability in the Volve field, wireline logs were used to train Extra-Trees, Ridge, Bagging, and XGBoost models. The Random Forest feature selection technique was applied to select the relevant logs as inputs for the models. Based on statistical metrics, the Extra-Trees model achieved the highest test accuracy of 0.996, RMSE of 19.54 mD, and MAE of 3.18 mD, with XGBoost coming in second. However, when the results were visualised, it was discovered that the XGBoost model was more suitable for the problem being tackled. The XGBoost model was a better predictor within the sandstone interval, while the Extra-Trees model was more appropriate in non-sandstone intervals. Since this study aims to predict permeability in the reservoir interval, the XGBoost model is the most suitable. These contrasting results demonstrate the importance of incorporating data visualisation techniques as an evaluation metric. Given the heterogeneity of the subsurface, relying solely on statistical metrics may not be sufficient to determine which model is best suited for a particular problem. © 2023 Sinopec Petroleum Exploration and Production Research Institute