Short-term　prediction　of　holiday　travel　demand　is　a　complex　but　key　issue　to　the　planning　and　management　of　tour　transportation　system　in　big　cities.　This　paper　develops　an　improved　spatial　and　temporal　correlation　long　short-term　memory　model　(STC-LSTM)　to　forecast　short-term　holiday　travel　demand　based　on　deep　learning　approach.　Analysis　results　show　six　kinds　of　tourist　flow　correlations　appears　in　different　sets　of　tourist　attractions,　and　27.94　percent　of　the　tourist　attractions　have　mid-　or　high-　positive　tourist　flow　correlation　with　others,　meaning　that　a　positive　synchronization　mechanism　exists　between　suburban　tourist　attractions　in　Beijing.　The　proposed　model　predicts　the　holiday　travel　demand　on　the　basis　of　the　historical　data　of　the　spatial　and　temporal　related　tourist　flows,　and　the　auxiliary　data　including　meteorological　data,　temporal　data,　and　Internet　search　index.　Based　on　actual　case　study　with　tourist　flow　data　of　the　suburban　tourist　attraction　in　Beijing,　the　proposed　STC-LSTM　is　carried　out　to　compared　with　other　conventional　prediction　approaches.　Results　show　that　the　proposed　approach　can　improve　the　prediction　accuracy　and　well　capture　the　different　spatial　and　temporal　correlations　of　tourist　flows.