Business forecasting remains a popular topic these days. A reliable business forecast often plays a vital part in an advertising campaign. The amount of attention acquired by posting an advertisement is one of the most essential criteria in determining the efficacy of the advertisement. The number of times that public users engage with a content signifies the amount of attention received, was measured by user engagement. With a good forecast, the advertisement could be promoted to a larger number of people. Facebook, as the most popular social media site, is favoured by majority of the advertisers. Therefore, this study addresses Facebook user engagement by forecasting the optimum date to post an advertisement. Different forecasting models, each with its own strengths and weaknesses, are used to model time series data with various properties. The objective of this study is twofold: to investigate the accuracy of the proposed Hybrid Prophet-LSTM that combines Long Short Term Memory (LSTM) and FBProphet (Prophet) and to study the holiday impact on user engagement forecasting on Facebook brand pages. Data from 3 popular brand pages in the period of June 2018 to March 2019 was used in the experiments. The results show that the proposed hybrid model outperforms both the standalone LSTM and Prophet across the datasets. Besides, it is found that holiday effect could generally increase forecast accuracy. The optimum date for an advertisement campaign can therefore be determined based on the most forecasted user engagement, which consequently enhances the business income. Keywords: Time Series forecasting, Hybrid forecasting, Business forecasting, Prophet, LSTM, Holiday effect