微軟銀行業(yè)大數(shù)據(jù)解決方案交流(存儲版)
【正文】 力以及最終消費(fèi)者的評價傾向 ? 按照產(chǎn)品屬性分析受眾情緒傾向 ? 按照品牌及業(yè)務(wù)伙伴分析影響力 ? 分析客戶在不同銷售渠道下的用戶體驗(yàn) ? 分析客服中心的業(yè)務(wù)績效如呼叫量，呼叫時長，解決狀態(tài)，客戶滿意度等 ? data分析客戶數(shù)據(jù)以及客戶網(wǎng)絡(luò)行為，社交媒體信息，對客戶需求有更深洞察力 關(guān)鍵指標(biāo) ? 營銷活動有效性 ? 各產(chǎn)品反應(yīng)比例 ? 渠道的有效性 ? 市場費(fèi)用投入產(chǎn)出比 ? 市場比例 ? 品牌接受度 ? 客戶滿意度 ? 最有影響力人群 ? 客戶滿意度 ? 呼叫總量，反應(yīng)速度 ? 客戶留存率 38 38 Generate a minimum of $100K in savings a year through automation of sentiment data and targeted customer marketing. By automating sentiment analysis, they can alleviate the pain of reacting too late to negative sentiment and avoid costly lawsuits. TBD Leveraging social data to determine customer sentiment and position products Situation Need Results Highlight Solution MS的大數(shù)據(jù)成功案例 Capital One社交網(wǎng)站客戶滿意度分析 39 MS的大數(shù)據(jù)成功案 例 Experian跨渠道營銷 Bundling ready to consume data with BI and industry accelerators for clear results Situation Need Results Highlight Solution 40 “ ” Connects to more than 1 billion signals 連接到超過 10 億的信號 /數(shù)據(jù)源 Across 15 leading social works, including Facebook 排名前 15位的社交網(wǎng)絡(luò)，包括 Facebook Generates a ‘Klout’ score for individual people, brands partners 為個人、 品牌及合作伙伴生成一個 ‘Klout’ 分?jǐn)?shù) Enables analysis, targeting and social graphs 在線影響力分析工具， 提 供 分析、 目標(biāo)和社交圖 MS的 大數(shù)據(jù)成功案 例 KLOUT 1 Perform A|B Testing of User Flows 2 Optimize Registration Funnels 3 Monitor consumer engagement retention (DAUs MAUs) 4 Flexibly track and report on user generated events 42 Serving Stores Signal Collectors (Java/Scala) Data Warehouse (Hive) () Event Tracker (Scala) Mobile (ObjectiveC) Analytics Cubes (SSAS) Klout API (Scala) Search Index (Elastic Search) Registrations DB (MySql) Profile DB (HBase) Streams (MongoDB) Dashboards (Tableau) Perks Analyics (Scala) Monitoring (Nagios) Data Enhancement Engine (PIG/Hive) Partner API (Mashery) KLOUT大數(shù)據(jù) MS解決方案架構(gòu) Requirement Hadoop Hive BI Query Engines Capture store all data Yes No Support queries against detail data Yes No Support interactive queries applications No Yes Support BI visualization tools No Yes 43 Event Tracker Architecture 43 Warehouse Instrument Collect Persist Query Report Tracker API Scala, Log Process Flume Cube Analysis Services Klout UI Scala, AJAX UX SELECT { [Measures].[Counter], [Measures].[PreviousPeriodCounter]} ON COLUMNS, NON EMPTY CROSSJOIN ( exists([Date].[Date].[Date].allmembers, [Date].[Date].[20230519T00:00:00]:[Date].[Date].[20230602T00:00:00]), [Events].[Event].[Event].allmembers ) DIMENSION PROPERTIES MEMBER_CAPTION ON ROWS FROM [ProductInsight] WHERE ({[Projects].[Project].[plusK]}) event_log tstamp string project string event string session_id bigint ks_uid bigint ip string json_keys arraystring json_values arraystring json_text
環(huán)評公示相關(guān)推薦
鄂ICP備17016276號-1