Fatty acid methyl esters (FAME) were synthesized from the waste cooking oil (WCO) by direct transesterification with methanol. The WCO was pretreated to increase the efficiency of FAME production with 1% of potassium methoxide as a catalyst. The free fatty acid of raw source was reduced using 2% of activated charcoal as adsorbent. The process variables were optimized using Box-Behnken design of Response Surface Methodology (RSM), and developed Artificial Neural Network (ANN) model to predict the FAME yield. The highest percentage of conversion (95%) was achieved at optimum conditions, for the catalyst concentration of 1%, alcohol to oil ratio of 6: 1, temperature of 75 degrees C and time of 60 s. The yield of biodiesel was estimated by higher R-2 values of RSM (0.98) and ANN (0.99), respectively. The produced FAME from pretreated WCO at 75 degrees C by microwave irradiation was examined by proton nuclear magnetic resonance (H-1 NMR), carbon nuclear magnetic resonance (C-13 NMR), Fourier transform infrared (FT-IR) spectroscopy, and gas chromatography-mass spectrometry (GC-MS). The esters exhibited their two characteristically strong absorption bands arising from carbonyl (C=O) at 1741 cm(-1) of fresh oil, and CeO stretching between 1300 and 1000 cm(-1) in the FT-IR spectra. A representative spectrum of (CNMR)-C-13 for the FAME from WCO was confirmed the presence of methyl esters in the biodiesel of ester carbonyl (-COO-) and C=O at 174.2 ppm and 51.4 ppm, respectively. The characteristic peak of 1H NMR at 1.00 ppm of methoxy protons was observed as a singlet at 3.67 ppm, which proved occurrence of the methyl ester (CH3COOR). In addition, a significant weight loss at 139 degrees C was observed through thermogravimetric (TG) analyses of FAME.