Online handwriting recognition, keypads, soft keys are some of the data entry techniques usedrnto enter data into mobile devices, such as smart phone, PDA etc. Data entry in these devicesrncould be either predictive or non-predictive. A word prediction method is a data entryrntechnique in which the first few characters of the word is written and the remaining arernpredicted. Among the data entry techniques, online handwriting recognition is commonlyrnused for handheld devices such as PDAs. When online handwriting recognition is combinedrnwith word prediction, the data entry process will be more efficient.rnIn this work, we have proposed a word prediction model for Amharic online handwritingrnrecognition. To design the model: a corpus of 131,399 Amharic words is prepared to extractrnstatistical information that is used to determine the value of N for the N-gram model, wherernthe value two (2) is considered as a result of the analyses made a combination of an Amharicrndictionary (lexicon) and a list of names of persons and places with a total size of 17,137 hasrnbeen used.rnTo show the validity of the word prediction model and the algorithm designed, a prototype isrndeveloped. Experiment is also conducted to measure the accuracy of the word predictionrnengine and a prediction accuracy of 81.39% is achieved.rnKeywords: Amharic Online Handwriting Recognition, Amharic word prediction model,rnN-gram model for Amharic word prediction, word prediction corpus