Difference between revisions of "ANLY482 AY2016-17 T1 Group6/Midterm Progress"

From Analytics Practicum
Jump to navigation Jump to search
Line 124: Line 124:
 
Each of these metrics will be calculated on for each month from January 1st to August 31st to establish time series trends.
 
Each of these metrics will be calculated on for each month from January 1st to August 31st to establish time series trends.
  
'''A. Relationship Score'''
+
'''A) Relationship Score'''
 +
 
 
The relationship score is given to each record in the Relationship Report and is to determine the strength of the relationship between a salesperson and an External/Internal party. The score focuses on two factors are Frequency of communication and Recency of communication.  
 
The relationship score is given to each record in the Relationship Report and is to determine the strength of the relationship between a salesperson and an External/Internal party. The score focuses on two factors are Frequency of communication and Recency of communication.  
 +
  
 
Purpose:  
 
Purpose:  
 +
 
1. To evaluate the relationship performance in terms of both building and maintaining them with internal and external parties.
 
1. To evaluate the relationship performance in terms of both building and maintaining them with internal and external parties.
 +
 
2. To evaluate the balance between internal and external relationships maintained by the salesperson
 
2. To evaluate the balance between internal and external relationships maintained by the salesperson
Formulation:  
+
 
Overall Relationship Score (ORS): Calculated for each internal and external relationship of the salesperson. Both X & Y variables will be standardized to give each equal weightage.
+
 
X: Total frequency of emails exchanged since Jan 1 2016 between the salesperson and the other party  
+
''Formulation:''
Y: The number of days since the last communication with the other party  
+
*Overall Relationship Score (ORS): Calculated for each internal and external relationship of the salesperson. Both X & Y variables will be standardized to give each equal weightage.
 +
*X: Total frequency of emails exchanged since Jan 1 2016 between the salesperson and the other party  
 +
*Y: The number of days since the last communication with the other party  
 +
 
 +
 
 
Formula = X+1/Y
 
Formula = X+1/Y
Explanation: 1/Y in this case is the recency factor as the number of days since the last contact will inversely affect the relationship score. (A higher number of days since last spoken will mean a lower relationship score)  
+
 
Total External to Internal Network Ratio of each salesperson
+
 
ΣORSE /ΣORSI
+
''Explanation:''
(ORSE: External Relationship Score, ORSI: Internal Relationship Score)
+
 
 +
1/Y in this case is the recency factor as the number of days since the last contact will inversely affect the relationship score. (A higher number of days since last spoken will mean a lower relationship score)  
 +
Total External to Internal Network Ratio of each salesperson:
 +
 
 +
ΣORSE /ΣORSI
 +
 
 +
ORSE: External Relationship Score, ORSI: Internal Relationship Score)
 +
 
 
Therefore, Sum of All External Relationship Scores divided by the Sum of All Internal Relationship Scores.
 
Therefore, Sum of All External Relationship Scores divided by the Sum of All Internal Relationship Scores.
  
B. Hot & Cold Relationships
 
  
The client advised us that a relationship can be considered considered Cold if no contact was made within 30 days and Hot if contact was made within the past 30 days. Therefore hot and cold relationships are a binary classification in this case. There can be cases in which people have not communicated within 30 days for a legitimate reason such as the contact being out of office etc. But we felt that 30 days is a lenient assumption for it is unusual that for an active conversations to not be for 30 days.  
+
'''B) Hot & Cold Relationships'''
 +
 
 +
The client advised us that a relationship can be considered considered Cold if no contact was made within 30 days and Hot if contact was made within the past 30 days. Therefore hot and cold relationships are a binary classification in this case. There can be cases in which people have not communicated within 30 days for a legitimate reason such as the contact being out of office etc. But we felt that 30 days is a lenient assumption for it is unusual that for an active conversations to not be for 30 days.  
 +
 
 +
'''C) Strong & Weak Relationships'''
 +
 
 +
Strong and Weak Relationships will be determined by comparing monthly relationship scores to the average baseline relationship score for January for all salespeople. Strong relationships in this case would be ones with above average relationship score and weak would be ones with below average relationship score.
 +
 
 +
'''D) Sales Stages'''
  
C. Strong & Weak Relationships
+
The absolute number of email threads belonging to each Sales Stage in the current month. (Determined by Subject Header Data)
• Strong and Weak Relationships will be determined by comparing monthly relationship scores to the average baseline relationship score for January for all salespeople. Strong relationships in this case would be ones with above average relationship score and weak would be ones with below average relationship score.
 
  
D. Sales Stages
+
'''E) Sales Conversion Rate'''
• The absolute number of email threads belonging to each Sales Stage in the current month. (Determined by Subject Header Data)
 
  
E. Sales Conversion Rate
+
The number of threads in a particular stage in current month divided by number of threads in that stage in the previous month.
The number of threads in a particular stage in current month divided by number of threads in that stage in the previous month.
 
  
 
</font></div>
 
</font></div>

Revision as of 23:44, 16 October 2016

MST Logo.jpeg

Home Team Project Overview Midterm Progress Final Progress Project Management Documentation


Recap & Objectives

Our sponsor, Trustsphere is a software company that provides relationship analytics solutions. Their products deliver insights that help clients across the globe improve key business issues including sales force effectiveness, enterprise-wide collaboration and corporate governance. The company engaged our team to utilize our technical and analytical capabilities to help them understand and tackle their business problem of little growth in sales and a longer than ideal sales cycle.

While the field of Sales Analytics has received plenty attention in the past, recent studies reveal that few companies have also delved into the area of Sales People Analytics. Salespeople communications to potential clients, especially in the B2B sphere, are wholly relied upon for marketing the company’s product. Furthermore, Steward et al. (2010) found that higher-performing salespeople also regularly activated their internal company networks, to coordinate a team of experts tailored to serve a particular customer. Just sales figures to evaluate salespeople performance covers a very narrow perspective as it disregards cycle time and in-progress pitches, therefore our team has defined our scope as to analyze the sales team’s internal and external communications to gain insight into their relationships with internal and external parties and to identify the sales stages that act as bottlenecks in the sales process.


Data Provided by Client

For this project, our team is working with two sets of data provided to us by TrustSphere:

A) Daily email communication data (main dataset)

This dataset contains year-to-date (up till 31 August 2016) records of daily email communication data of all 19 Trustsphere sales people across the globe. This data includes the following variables:

Date: Includes the date and time of a particular email being sent

Originator address: Sender email address

Recipient address: Receiver email address

Direction: Nature of communication (internal, inbound or outbound)

MsgID: Unique message ID of emails sent

Email Subject: Email subject header


Figure 1 - Original Dataset


B) Staff List

The dataset lists all of TrustSphere staff (57) with the following variables:


Name

Hierarchy

Department

Position

Location


We were also provided with a Relationship dataset, as mentioned previously in the proposal, which contained individual records of salespeople relationships – however we are not using this dataset in any of our analyses.


Exploratory Research & Revision of Scope

Our research objectives under the ‘Scope of Work’ section of our proposal remain largely unchanged. However, we have decided to remove most of the social network visualisations as TrustSphere is already working on that area.

We also had the opportunity to speak to Ms. Annabel Koh from the Sales Department. She provided us with a clearer idea of the sales stages so we could incorporate their importance (weightage column) into our analysis of the subject headers.

Figure 2 - Sales stages and its importance in the sales cycle.

She also gave us insight into other areas she thought would be useful to know for the Sales Department:


a. Time taken to transit between sales stages

b. Conversion rates

  • Response rate of prospects into meetings
  • Conversion rate from meetings into Proof of Concept (POC) trials

c. Amount of time spent communicating internally

  • Worries of over-collaboration

d. Overlap of relationships

  • Are there different salespeople pursuing/serving the same account?


Finalised Scope of Work & Analysis Metrics
Calculations of Metrics

Each of these metrics will be calculated on for each month from January 1st to August 31st to establish time series trends.

A) Relationship Score

The relationship score is given to each record in the Relationship Report and is to determine the strength of the relationship between a salesperson and an External/Internal party. The score focuses on two factors are Frequency of communication and Recency of communication.


Purpose:

1. To evaluate the relationship performance in terms of both building and maintaining them with internal and external parties.

2. To evaluate the balance between internal and external relationships maintained by the salesperson


Formulation:

  • Overall Relationship Score (ORS): Calculated for each internal and external relationship of the salesperson. Both X & Y variables will be standardized to give each equal weightage.
  • X: Total frequency of emails exchanged since Jan 1 2016 between the salesperson and the other party
  • Y: The number of days since the last communication with the other party


Formula = X+1/Y


Explanation:

1/Y in this case is the recency factor as the number of days since the last contact will inversely affect the relationship score. (A higher number of days since last spoken will mean a lower relationship score) Total External to Internal Network Ratio of each salesperson:

ΣORSE /ΣORSI

ORSE: External Relationship Score, ORSI: Internal Relationship Score)

Therefore, Sum of All External Relationship Scores divided by the Sum of All Internal Relationship Scores.


B) Hot & Cold Relationships

The client advised us that a relationship can be considered considered Cold if no contact was made within 30 days and Hot if contact was made within the past 30 days. Therefore hot and cold relationships are a binary classification in this case. There can be cases in which people have not communicated within 30 days for a legitimate reason such as the contact being out of office etc. But we felt that 30 days is a lenient assumption for it is unusual that for an active conversations to not be for 30 days.

C) Strong & Weak Relationships

Strong and Weak Relationships will be determined by comparing monthly relationship scores to the average baseline relationship score for January for all salespeople. Strong relationships in this case would be ones with above average relationship score and weak would be ones with below average relationship score.

D) Sales Stages

The absolute number of email threads belonging to each Sales Stage in the current month. (Determined by Subject Header Data)

E) Sales Conversion Rate

The number of threads in a particular stage in current month divided by number of threads in that stage in the previous month.


Data Cleaning & Transforming


Future Tasks and Deliverables


In Progress: Preliminary Calculations & Testing