Stock price forecasting provide valuable insight to the investor to facilitate well-informed investment decision making. The aim of this study is to examine the calendar anomalies i.e. DOW in Pakistan stock exchange though Artificial intelligence techniques. For this purpose, Support vector machine (SVM), Decision Tree (DT) and Artificial Neural Network is used to forecast the daily stock prices. The daily stock prices data of KSE100 index ranges from May,1994 to August 2023 is used as out variable while stock open, close, high and low prices are used as features/input variables. The training and testing ratio was 80:20 means 80% of the data was used in training and the 20% values were utilized for forecasting. To evaluate the accuracy of predictions, mean square error (MSE), root mean square error (RMSE), mean absolute error (MAE)/mean absolute deviation (MAD), mean absolute percent error (MAPE), and R-squared (R^2) are taken as decision criteria. The daily forecasted stock prices show the almost zero error on Tuesday, Wednesday and Thursday in SVM. Decision tree show very low error in actual and forecasted stock prices. Therefore, it is concluded that, the DOW anomalies exist in KSE100 index of PSX. Results show that, SVM can better predict the stock prices than DT and ANN. These results conclude that the forecasted stock prices are much closer to actual daily stock price means the daily stock prices can be forecast in KSE100 index. These finding contradicts the Efficient market hypothesis and conclude that the Pakistan stock exchange (PSX) is weak-form inefficient market.