With　the　development　of　China＇s　economy　and　the　continuous　increase　of　national　income,　more　and　more　retail　investors　are　devoted　to　stock　management,　but　they　lack　professional　knowledge　and　skills,　so　it　is　difficult　for　them　to　make　profitable　trading　decisions.　In　addition,　the　distribution　of　resources　in　China　is　uneven,　the　quality　and　service　level　of　financial　institutions　are　restricted　by　regions,　and　there　is　a　big　gap　between　the　service　levels　of　financial　institutions　in　different　regions.　To　effectively　solve　this　problem,　a　cloud　computing-based　open　and　shared　auxiliary　transaction　decision-making　platform　for　multi-tenant　and　multi-organization　is　proposed　and　constructed.　Let　the　investment　and　wealth　management　services　of　financial　institutions　with　high　quality　and　service　level　be　able　to　cover　underdeveloped　areas.　At　the　same　time,to　better　personalize　the　recommendation　for　users,　and　satisfy　the　user＇s　ability　to　quickly　screen　financial　institutions　that　meet　their　own　requirements　from　a　large　number　of　financial　institutions,　a　Slope　One　algorithm　that　improves　the　calculation　method　of　project　similarity　is　proposed.　Considering　the　user＇s　project　on　the　basis　of　scoring,　the　final　similarity　is　calculated　by　integrating　item　attributes,　news　attributes　and　time　factors.　This　method　can　effectively　improve　the　recommendation　accuracy　and　solve　the　cold　start　problem　to　a　certain　extent.