+ All Categories
Home > Documents > Automated Time Series Forecasting Process Valentin Todorov January 23, 2013 Assurant Specialty...

Automated Time Series Forecasting Process Valentin Todorov January 23, 2013 Assurant Specialty...

Date post: 17-Dec-2015
Category:
Upload: stephany-carpenter
View: 215 times
Download: 2 times
Share this document with a friend
12
Automated Time Series Forecasting Process Valentin Todorov January 23, 2013 Assurant Specialty Property
Transcript
Page 1: Automated Time Series Forecasting Process Valentin Todorov January 23, 2013 Assurant Specialty Property.

Automated Time Series Forecasting Process

Valentin TodorovJanuary 23, 2013

Assurant Specialty Property

Page 2: Automated Time Series Forecasting Process Valentin Todorov January 23, 2013 Assurant Specialty Property.

Objective

• Develop a time series forecast of incoming calls to the company’s call centers– Create a forecast for calls related to mortgages and a separate one for

HELOCs• Re-forecast weekly using the most recent actual call data• Distribute results to managers in the call centers• Implement the forecasting process within one month• Budget $0 …. excluding the man-hours to develop the process

All of that should be accomplished with SAS

2

Page 3: Automated Time Series Forecasting Process Valentin Todorov January 23, 2013 Assurant Specialty Property.

Challenging and messy

Time consuming Error prone

3

Page 4: Automated Time Series Forecasting Process Valentin Todorov January 23, 2013 Assurant Specialty Property.

A sleek solution

Dropbox

Use a CRON job to monitor the dropbox, and test every 5 minutes for the existence of a

specific file. If a file is present, execute a SAS code

Every Monday morning an employee from our call

center sends via FTP a file with the previous week’s

actual call volumes

Import and clean the data, re-forecast and send results via

email

CRON is a job scheduler in UNIX. For more information see http://en.wikipedia.org/wiki/Cron

The only human in this process is the one who sends the file via FTP

4

Page 5: Automated Time Series Forecasting Process Valentin Todorov January 23, 2013 Assurant Specialty Property.

Dropbox

• Folder located on the servers• CRON job performs a test every 5 minutes for the existence of files

[[ -f “/sas/shared/dropbox/u99/MortgCo/MortgCo_${source_type}_update.csv” ]] &&MortgCo_haz_update.csv – Calls related to mortgage loansMortgCo_heloc_update.csv – Calls related to HELOC loans

• If files exist, BASH code is executed which kicks off the SAS code

5

Page 6: Automated Time Series Forecasting Process Valentin Todorov January 23, 2013 Assurant Specialty Property.

SAS code

• Import new files with actual call volume data from previous week• Check for data integrity and consistency• Append to historical files and clean up• Run the forecasts• Package the data• Send forecasts via email to managers in call center

6

Page 7: Automated Time Series Forecasting Process Valentin Todorov January 23, 2013 Assurant Specialty Property.

Call volume has a consistent daily pattern

• The call volume follows a pattern that repeats on a weekly basis• The pattern is interrupted by public holidays, which are visible on the

graph• No calls during weekends

7

Page 8: Automated Time Series Forecasting Process Valentin Todorov January 23, 2013 Assurant Specialty Property.

The forecasting process is driven by macros

8

Page 9: Automated Time Series Forecasting Process Valentin Todorov January 23, 2013 Assurant Specialty Property.

Check data integrity of incoming files

• Calculate length of latest file with actual data – should be 7 days• Check if the dates in the file are the last 7 days

9

If any condition fails, stop the process and send warning emails!

Page 10: Automated Time Series Forecasting Process Valentin Todorov January 23, 2013 Assurant Specialty Property.

ARIMA Forecast

• The model is ARIMA– Mortgages: AR (5,10,15,20) MA (5) with a difference = 5– HELOC: AR (5,10,15) MA (4) with a difference = 5

• Developed using two years of historical data• The forecast has 24% higher accuracy compared to the incumbent

model– Accuracy: Number of days forecast has a variance of less than 8%

10

Page 11: Automated Time Series Forecasting Process Valentin Todorov January 23, 2013 Assurant Specialty Property.

Email final results

11

Page 12: Automated Time Series Forecasting Process Valentin Todorov January 23, 2013 Assurant Specialty Property.

Valentin [email protected]://www.linkedin.com/in/vatodorov/

12


Recommended