Seminar #50 - Salesforce Data, Clean, Visualize, Analyze, & Dashboard

You can access Salesforce data directly inside Exploratory with the latest release (v6.6). In this seminar, Kan will demonstrate how you can access the data and introduce some of the data visualization and analysis methods to maximize the value of your Salesforce data.

- Access and Query Data
- Transform and Visualize Data
- Create Dashboard
- Forecast Leads with Prophet
- Predict for Customer Win
- Use Parameters to Interact

Subscribe ↓
https://www.youtube.com/channel/UCOVfLaSQBvMRwZCyiccq4Iw

Twitter ↓
https://twitter.com/ExploratoryData

UI Tool: Exploratory(https://exploratory.io/)
Exploratory Online Seminar: https://exploratory.io/online-seminar

Transcript

1. EXPLORATORY Online Seminar #50 X Get, Clean, Visualize, and Analyze Salesforce Data with Exploratory
2. Kan Nishida CEO/co-founder Exploratory Summary In Spring 2016, launched Exploratory, Inc. to democratize Data Science. Prior to Exploratory, Kan was a director of product development at Oracle leading teams to build various Data Science products in areas including Machine Learning, BI, Data Visualization, Mobile Analytics, Big Data, etc. While at Oracle, Kan also provided training and consulting services to help organizations transform with data. @KanAugust Speaker
3. 3 Questions Communication Data Access Data Wrangling Visualization Analytics (Statistics / Machine Learning) Data Science Workflow
4. 4 Questions Communication (Dashboard, Note, Slides) Data Access Data Wrangling Visualization Analytics (Statistics / Machine Learning) ExploratoryɹModern & Simple UI
5. EXPLORATORY Online Seminar #50 X Get, Clean, Visualize, and Analyze Salesforce Data with Exploratory
6. Agenda • Get Data • Clean and Transform Data • Visualize Data • Create, Publish, Share, and Schedule Dashboard • Parameterize Dashboard • Forecast Leads • Predict Win 6
7. Agenda • Get Data • Clean and Transform Data • Visualize Data • Create, Publish, Share, and Schedule Dashboard • Parameterize Dashboard • Forecast Leads • Predict Win 7
8. Supported Salesforce Editions 8 • Professional • Enterprise • Unlimited • Performance • Developer
9. UI SQL 2 Modes
10. UI SQL 2 Modes
13. 13 Select a table you want to import data for.
14. 14 Select columns.
15. Use Filter to limit the data. 15
16. Once the data is imported, it automatically generates the Summary view. 16
17. UI SQL 2 Modes
18. SQL (SOQL)
19. You can write SQL (SOQL) Queries to get data from Salesforce.
20. Agenda • Get Data • Clean and Transform Data • Visualize Data • Create, Publish, Share, and Schedule Dashboard • Parameterize Dashboard • Forecast Leads • Predict Win 20
21. Clean and Transform data from the column header menu.
22. You can update any of the existing data wrangling steps. 22
23. Click ‘Re-import’ button to get the latest data from Salesforce. 23
24. All the data wrangling steps will be automatically applied. 24
25. Agenda • Get Data • Clean and Transform Data • Visualize Data • Create, Publish, Share, and Schedule Dashboard • Parameterize Dashboard • Forecast Leads • Predict Win 25
26. Click the chart icon to quickly create a chart. 26
27. 27 It will create a new chart under the Chart view.
28. 28 You can customize the chart by updating the column assignments and the chart configuration.
29. But, here is one thing…
30. 30 The stage names are sorted alphabetically…
31. It’s better to sort them following the natural order of the stages. 31
32. Prospecting Conversion Hearing 32 Proposal This order is confusing… Stages for Opportunity
33. Prospecting Conversion Hearing 33 Proposal This is intuitive! Stages for Opportunity
34. 1 3 4 34 Factor - Ordered Categories 2 Prospecting Conversion Hearing Proposal
35. Stage Hearing Conversion Proposal Prospecting Character (Categorical) 35 Stage Level Prospecting 1 Hearing 2 Proposal 3 Conversion 4 Factor (Ordinal)
38. A new data wrangling step is added to the Step pane. 38
39. 39 The values are sorted following the level setting for the Factor data type columns.
40. Open the chart and move the Pin to the latest step. 40
41. Currently, the stages are ordered from the bottom to the top. 41
42. You can change the direction of the order. 42
43. Agenda • Get Data • Clean and Transform Data • Visualize Data • Create, Publish, Share, and Schedule Dashboard • Parameterize Dashboard • Forecast Leads • Predict Win 43
44. 44 Here’s a typical Dashboard in Exploratory.
45. 45 Numbers Analytics - Forecasting Analytics - Cohort Analysis Map Chart You can bring in various types of numbers and charts.
46. 46 You can bring in various types of data.
47. 47 And…
48. Since you can create charts with different steps of Data Wrangling…
49. 49 You can bring in charts that are based on different steps.
50. 50 Create a new Dashboard.
51. 51 Add an existing chart.
53. 53 Adjust the height of each row section by drag-and-drop.
54. 54 Adjust the width of each column section by drag-and-drop.
55. 55 Click ‘Run’ button to preview the output.
56. 56 By clicking the ‘Re-Import Data’ button, you can query the latest data from Salesforce and apply all the data wrangling steps that are required to generate the charts.
57. Publish the Dashboard to: 1. Share 2. Interact 3. Schedule 57
58. Publish the Dashboard either in Private or Public mode.
59. 59 Once it’s published the Dashboard will have its own unique URL.
60. 60 Open the Dashboard in a web browser.
61. 61 You can invite specific people to share your Dashboard securely.
62. 62 Type their email addresses and write an inviting message.
63. 63 They will receive an email like the below.
64. 64 If they don’t have Exploratory accounts yet they can sign up for free ‘Viewer’ accounts.
65. Schedule your Dashboard so that the data inside the Dashboard is kept up-to-date automatically. 65
66. You can subscribe a notification email every time the scheduling job is run. 66
67. 67 Other invited members can also subscribe the notification emails.
68. You will receive notification emails with thumbnail images. 68 is updated. is updated.
69. 69 Dashboard Dashboard Exploratory Desktop Exploratory Server Publish OAuth OAuth How the scheduling works.
70. 70 Take a look at the past seminar for more details on the lifecycle of Dashboard!
71. Select ‘How To (Tutorials)’. 71
72. Click on ‘Dashboard’. 72
73. Click on ‘Dashboard’. 73
74. Agenda • Get Data • Clean and Transform Data • Visualize Data • Create, Publish, Share, and Schedule Dashboard • Parameterize Dashboard • Forecast Leads • Predict Win 74
75. 75 Me Team Mates I want data for Europe. I want data for Africa. I want data for Asia. Exploratory Server Everybody has a different interest. Publish
76. 76 By parameterizing the Dashboard, you can let them choose which part of the data they want to see.
77. • Data Source Filter • Step Filter • Chart Filter 3 Type of Filters
78. You can create Filters in the data import dialog so that you can limit the data you query from Salesforce. 78
79. 79 You can parameterize this Filter!
80. 80 You can create Filters on top of the imported data as data wrangling steps.
81. 81 You can parameterize the Step Filter as well!
82. You can create Filters inside the Chart. This Chart Filter works only for the particular chart. 82
83. 83 And, you can parameterize the Chart Filter as well!
84. 84 Click the Parameter button.
85. 85 All the parameters that are required to generate the chart data will automatically show up in the pane.
86. For the Dashboard, all the parameters that are required to generate data for all the charts inside the Dashboard are automatically added to the Parameter pane. 86
87. For the published Dashboard, you can open the Parameter pane and turn on the interactive mode to start using the parameters. 87
88. A bit more details on how the Parameter works.
89. 89 1. Data Source 2. Create Calculation 3. Filter Created data wrangling steps and charts. Chart 2 Chart 1
90. 90 Closed Date 1. Data Source 2. Create Calculation 3. Filter Created Filters. Probability Type Chart 2 Chart 1
91. 91 Closed Date 1. Data Source 2. Create Calculation 3. Filter Created Dashboard with Chart 2. Dashboard 1 Probability Type Chart 2 Chart 1
92. 92 Closed Date 1. Data Source 2. Create Calculation 3. Filter Dashboard 1 Probability When you open the Parameter pane you will see‘Closed Date’ and ‘Probability’ parameters automatically.
93. 93 Closed Date 1. Data Source 2. Create Calculation 3. Filter Now, we added Chart 1 to the Dashboard. Dashboard 1 Probability Type
94. Dashboard 1 Type 94 Closed Date 1. Data Source 2. Create Calculation 3. Filter When you open the Parameter pane, the ‘Stage’ parameter is automatically added. Probability
95. Dashboard 1 Type 95 Closed Date 1. Data Source 2. Create Calculation 3. Filter Probability If we change the Probability parameter only the Chart 2 gets updated.
96. Dashboard 1 Type 96 Closed Date 1. Data Source 2. Create Calculation 3. Filter Probability If we change the Stage parameter only the Chart 1 gets updated.
97. Dashboard 1 Type 97 Closed Date 1. Data Source 2. Create Calculation Probability If we change the Closed Date parameter all the steps and the charts will be updated. 3. Filter
98. You can also parameterize the SQL queries.
103. Agenda • Get Data • Clean and Transform Data • Visualize Data • Create, Publish, Share, and Schedule Dashboard • Parameterize Dashboard • Forecast Leads • Predict Win 103
104. 104 Can we forecast how the number of leads will look like in the next 12 months?
105. 105 Want to forecast the number of leads in the next 12 months. Actual Forecasted
106. • Time interval between data has to be same throughout the data • Day with NA is not allowed • Seasonality with multiple periods (Week and Year) is hard to handle • Parameter tuning is hard and requires a forecasting expert level knowledge. Problems with Traditional Time Series Model
107. • A ‘curve fitting’ algorithm to build time series forcasting models. • Designed for ease of use without expert knowledge on time series forecasting or statistics. • Built by Data Scientists (Sean J. Taylor & co.) at Facebook and open sourced. (https:// facebook.github.io/prophet) Prophet Sean J. Taylor @seanjtaylor
108. Build a model by finding a best smooth line which can be represented as sum of the following components. • Overall growth trend • Seasonality - Yearly, Weekly, Daily, etc. • Holiday effects - X’mas, New Year, July 4th, etc. • External Predictors Prophet - Additive Model
109. 109 Lead Data
113. Agenda • Get Data • Clean and Transform Data • Visualize Data • Create, Publish, Share, and Schedule Dashboard • Parameterize Dashboard • Forecast Leads • Predict Win 113
114. 114 Can we predict which opportunities we can win?
115. 115 Algorithm Model Build a Prediction Model. Conversion Age Time Country Industry TRUE 60 120 Japan Ad FALSE 45 55 US Medical FALSE 52 20 US Media TRUE 48 140 Japan Ad TRUE 53 80 UK Bank FALSE 35 30 Japan Media
116. 116 Predict Conversion Age Time Country Industry TRUE 25 120 Japan Ad FALSE 23 55 US Media FALSE 40 150 US Ad Conversion Age Time Country Industry ? 25 120 Japan Ad ? 23 55 US Media ? 40 150 US Ad Algorithm Model Conversion Age Time Country Industry TRUE 60 120 Japan Ad FALSE 45 55 US Medical FALSE 52 20 US Media TRUE 48 140 Japan Ad TRUE 53 80 UK Bank FALSE 35 30 Japan Media
117. 117 A model is a definition of a pattern the algorithm has captured in the data. Algorithm Model Conversion Age Time Country Industry TRUE 60 120 Japan Ad FALSE 45 55 US Medical FALSE 52 20 US Media TRUE 48 140 Japan Ad TRUE 53 80 UK Bank FALSE 35 30 Japan Media
118. 118 Not just for the prediction, we can also use it to learn a lot about the patterns in data. Insight • Which variables have stronger relationship with the target variable. • How are they related? • Are they significant? • What is the quality if we used this model to predict? Algorithm Model
119. 119 Opportunity Data
120. 120 The StageName column indicates whether we have won a given opportunity or not.
121. 121 What are the characteristics of these ‘Won’ opportunities?
122. In order to use the Correlation Mode and build a prediction model, we need to convert the StageName variable to Logical (True / False) data type. 122
123. Create a calculation that returns TRUE if a given value is ‘Closed Won’. 123
125. 125 11.7% of the existing opportunities are ‘Closed Win’.
126. 126 Click ‘Correlate’ button to open the Correlation mode.
127. Select ‘Is_Won’ variable as the target variable.
128. It shows the relationship between the Is_Win and all other variables with the charts along with metrics.
129. Sort the columns based on the AUC values, which indicate the strength of the relationship. 129
130. The ‘CallAmount’ has a strong relationship with the ‘Is_Won’. 130
131. We want to build a prediction model, but which one?
132. Numeric TRUE/FALSE TRUE/FALSE + Time Linear Regression Random Forest / XGBoost Statistical Learning Machine Learning Logistic Regression Cox Regression Survival Forest 132 Regression Model Classification Model Survival Model Data Type Statistical Learning Machine Learning Statistical Learning Machine Learning Random Forest / XGBoost
133. Let’s try with Logistic Regression model.
134. Select multiple variables and select one of the prediction model algorithms. 134
135. 135 A logistic regression model is created to predict the probability of winning.
136. Under the ‘Prediction’ tab, you can see how the probability of winning changes as the values in a given variable change. 136
137. 137 Under the Importance tab, you can see which variables are more important to predict the probability of winning.
138. 138 Under the Summary tab, you can see the quality of the prediction model.
139. 139 Under the Data tab, you can see the predicted result for all the existing accounts.
140. 140 This prediction result is for the existing data for which we know the answer already.
141. But, we want to predict the probability of winning for the future opportunities, not the past opportunities.
142. You can predict for the future opportunities by using the model we have just created.
143. 143 Import a new opportunity data.
145. 145 Select the model we have just created under the Analytics view.
146. 146 A set of new columns is added as the prediction values.
147. That’s it for today!
148. Next Seminar
149. EXPLORATORY Online Seminar #52 7/7/2021 (Wed) 11AM PT Machine Learning - Variable Importance
151. Information Email kan@exploratory.io Website https://exploratory.io Twitter @ExploratoryData Seminar https://exploratory.io/online-seminar
152. Q & A 152
153. EXPLORATORY 153