Logistics　demand　forecasting　is　the　foundation　of　logistics　management,　effective　logistics　demand　forecasting　for　a　balance　of　supply　and　demand　of　logistics　service　that　has　a　positive　meaning.　This　paper　constructs　the　index　system　which　is　suitable　for　the　forecasting　of　logistics　demand　in　Beijing　City　by　studying　the　current　situation　of　the　development　of　logistics　demand　in　Beijing,　finally,　grey　neural　network　model　is　established　according　to　the　actual　data　and　a　simulation　prediction　was　carried　out　on　this　basis.　The　experimental　results　show　that　the　model　for　the　short-term　trend　of　dynamic　of　logistics　demand　forecast　in　Beijing　has　a　good　prediction　effect;　the　results　also　can　be　used　as　the　basis　for　planning　and　control　of　logistics　in　Beijing　city　in　the　future.