1. Objective:
  We want to predict the VPN usage of employees based on the frequency of use of other apps.

2. License: Free to use, collected by Splunk.

3. Data Source:
  Corporate app usage from an anonymous company.

4. Data Set Information:
  The dataset covers just under three months of aggregate app usage.

5. Field Meanings:
  A. _time: UNIX epoch time
  B. The remaining fields (app names anonymized) contain the number of logins during that day.

6. Parameter Selection:
  A. Dashboard: Predict Numeric Fields
      Settings:
    1) Search: | inputlookup app_usage.csv
    2) Field to Predict: RemoteAccess
    3) Fields to Use: CRM, CloudDrive, HR1, Webmail

  B. Dashboard: Cluster Numeric Fields
        Settings:
    0) Search: | inputlookup app_usage.csv
    1) Model name: N/A
    2) Fields to preprocess: CRM, CloudDrive, ERP, Expenses, HR1, HR2, ITOps, OTHER, Recruiting, RemoteAccess, Webmail
    3) Apply StandardScaler
    4) Apply PCA to reduce to 3 fields
    5) Algorithm: Spectral Clustering
    6) Fields to use: PC_1, PC_2, PC_3
    7) K: 3