{"id":7324,"date":"2016-01-18T09:52:38","date_gmt":"2016-01-18T04:22:38","guid":{"rendered":"http:\/\/ucanalytics.com\/blogs\/?p=7324"},"modified":"2016-09-11T11:10:27","modified_gmt":"2016-09-11T05:40:27","slug":"business-process-optimization-call-center-case-study-example-part-2","status":"publish","type":"post","link":"https:\/\/ucanalytics.com\/blogs\/business-process-optimization-call-center-case-study-example-part-2\/","title":{"rendered":"Process Optimization & Real Time Analytics – Case Study Example (Part 2)"},"content":{"rendered":"
\"Ying<\/a>

Yin Yang Jigsaw – Real Time Analytics Case Study Example – by Roopam<\/p><\/div>\n

\n

This is a continuation of the case study example for\u00a0optimization of a business process. You can find the previous part at\u00a0this link<\/a>. In this case study example, you are helping a company reduce their process turn-around-time through advanced analytics and data science. You will use\u00a0some of the key data science activities including business\u00a0process optimization, customer &\u00a0agent profiling, linear programming, and real-time analytics.\u00a0But before we do that, let’s decipher some similarities between this problem and jigsaw puzzles. As you will notice later, on some metaphysical level, the solution to this problem is about solving a jigsaw puzzle of yin yang to produce harmony.<\/p>\n

Optimization of Jigsaw Puzzles<\/span><\/h2>\n

For over 250 years jigsaw puzzles are among the most popular past times for youngsters and adults alike. The origins of\u00a0jigsaw puzzles, traced back to the 18th century, were\u00a0about putting together pieces of maps to help children\u00a0learn geography.\u00a0Solving a jigsaw puzzle requires the player to connect the right pieces together to complete the picture. Among the many strategies to\u00a0solve the game, a commonly used strategy is to classify and group the pieces with similar colors before connecting the pieces.<\/p>\n

The objective of the solution for this case study example is to solve a jigsaw puzzle between callers and agents. The purpose of this solution is to patch the callers to the right agents so that the overall call duration can be minimized. The underlining assumption is that certain agents are better suited to solve a certain kind of problems. Moreover, personality and demographic profile of certain agents\u00a0enable them\u00a0to have harmonious and purposeful communication with the\u00a0callers of a certain profile.<\/p>\n

\"Caller<\/a>

Real Time Analytics – Automated Intelligence to connect callers with agents to minimize call duration<\/p><\/div>\n

Call Center Case Study Example<\/span><\/h2>\n

Back to the case study example where you are helping\u00a0Cut-to-the-Chase, an inbound call center for a digital television network, to swiftly resolve customer complaint and grievance calls. As discussed in the previous part<\/a>, Cut-to-the-Chase has an average call handle time of 12\u00a0minutes with close to\u00a04 minutes of wait time for a customer call. The objective here is to reduce\u00a0the average call handle time (without hold time) to 5 and a half minutes from 8 minutes. This will be quite an elaborate solution with the following steps<\/p>\n

    \n
  1. Unsupervised learning<\/strong> to segment callers\u00a0into different profiles based on their demographic, usage and complaints log\u00a0information<\/li>\n
  2. Supervised learning<\/strong> to identify the propensity of an\u00a0agent to resolve a query for different\u00a0caller profiles within desired query resolution time<\/li>\n
  3. Linear\u00a0programming<\/strong> for real-time analytics\u00a0to patch the right caller\u00a0profile with the agent\u00a0profile based on propensity scores derived in step 3<\/li>\n<\/ol>\n

    I will primarily focus on step 3 of real-time analytics and optimization through integer programming in this case study example. I will briefly discuss steps 1, and 2 in the next few segments. We have discussed both unsupervised<\/a> and supervised<\/a> learning algorithms in a great detail in two different case study examples on YOU CANalytics. Please read those case studies to gain an intuitive and practical understanding of these learning algorithms.<\/p>\n

    Step 1: Caller Profiling –\u00a0Unsupervised Learning<\/span><\/h2>\n
    \"Slide3\"<\/a>

    Unsupervised learning – Case Study Example<\/span><\/p><\/div>\n

    The first step for this solution is to segment the customer base into groups based on the similarity between them. The customer base is segmented based the following broad classes of variables.<\/p>\n