Accommodating left turns at un-signalized intersections is one of the most challenging problems in traffic engineering. Over the last forty years, a small number of studies developed guidelines for traffic engineers to help decide when a left turn lane is warranted for a given situation. Building on these previous attempts, the current study not only develops warrants for the left turn lane at an unsignalised intersection but also a refined decision support system (DSS) for assessing the likely benefits of left-turn lane installations. The developed warrants use total delay (veh.sec/hour) and total stops (number) on the subject link as the warrant criteria, and the trigger level differs by road category. The developed DSS on the other hand, is designed to predict the likely benefits of installation of an exclusive left turn lane at an un-signalized intersection. The benefits are measured in terms of delay savings, reductions in the total number of stops, increases in fuel efficiency, and reductions in emissions. The first step in developing the left turn lane warrants and the DSS was to use microscopic simulation to model several real-world un-signalized intersections with different geometric. After carefully calibrating these models, several scenarios which cover a wide range of operational conditions (opposing, advancing, left turning volumes speed etc,) were simulated. The output fiom these simulation runs was then used to train a set of Multi-layer Perceptron Neural Networks (NNs), and to generalize the results from the models' runs. These NNs can therefore serve as a DSS for predicting the likely benefits of left turn lane installations. In addition, new warrants were developed for left turn lane installations based on delay as well as percent stops as warrant criteria.