BookmarkSubscribeRSS Feed
Babloo
Rhodochrosite | Level 12

Can someone give ideas to apply time series analysis in banking data which holds customer information? What 'proc' to be used in SAS EG?

13 REPLIES 13
Babloo
Rhodochrosite | Level 12

Any helpful answers?

Babloo
Rhodochrosite | Level 12

Any helpful answers?

udo_sas
SAS Employee

Hello -

published a nice overview on YouTube: Working with Time Series Data Using SAS/ETS - YouTube

Thanks,

Udo

Babloo
Rhodochrosite | Level 12

Thanks for the video.

May I request you to get me the similar video or document to accomplish the same via EG? Because SAS/ETS is not licensed for my site.

Kurt_Bremser
Super User

SAS/ETS is the primary SAS tool for time series analysis. Without it, you will have to do your analysis with the basic SAS tools.

We might be able to give you hints if you provide information about your data structure and the insights you need to gain.

Babloo
Rhodochrosite | Level 12

Unfortunately I don't have a data at the moment. However, if you can provide insights for some general scenarios (it can be any) where Time series is applicable for, it would be fine for me to expand my thoughts.

Reeza
Super User

The proc depends on the type of analysis required. If you don't have ETS you'll have a lot of work to do to prep your data ahead of time.

Time series is required when you want to look for trends in data - is there a seasonality in customer accounts balance - i.e. best time to make credit card offers? best time to make offers for investments besides RSP season?

Is there a particular time when you gain/lose customers? Is this related to a marketing effort?  Has a marketing effort affected the account balance of clients?

Babloo
Rhodochrosite | Level 12

I would request for an example or some documents for the below points as you mentioned.

Time series is required when you want to look for trends in data - is there a seasonality in customer accounts balance - i.e. best time to make credit card offers? best time to make offers for investments besides RSP season? Yes


Is there a particular time when you gain/lose customers? Is this related to a marketing effort?  Has a marketing effort affected the account balance of clients? Yes


I work for some financial institutions where I would like to find out the reason for gain/lose customers in a particular time. There are also a financial institution who would like to know best time to make credit card (or other campaign) offers.


If you can provide example to do these analysis (or insight) I can check with the financial institution to provide the data in case the data which I hold is not enough to kick off this analysis.


Thanks in advance for your help!

Babloo
Rhodochrosite | Level 12

Any helpful answers?

Babloo
Rhodochrosite | Level 12

Any helpful answers?

Babloo
Rhodochrosite | Level 12

May I request experts to provide some insights?

gergely_batho
SAS Employee

Hi,

We only know that you have time series data of a bank about customers.

Probably you have their monthly or daily balance or even their transactions (time stamped data).

If you don't have SAS/ETS your can use STAT and of course Base.

Some examples you can do with time series and time stamped data:

-aggregating balances or transactions to hourly, daily, weekly levels overall, by customer or by some customer group.

-aggregating by hour, by day of the week, day of the month - this way you can detect seasonality

-you can use time as independent variable and balance or usage (or some other dependent variable) in a regression to detect trends

-you can combine the two. For example create dummy variables from day of week, and use time as continuous variable -> detecting seasonality and trends

-you can extract various aggregations from time series or time stamped data on various level, then use these as input variables (together with demographic and marketing varaiables) in a predictive model (to predict customer behaviour: balance, churn, propensity, etc.).

Some technical stuff:

  It is relatively easy to derive many complex aggregation measures for each customer (for example "number of ATM transactions two week before Christmas", "time difference between last 2 transactions") using a single data step.

  proc means comes handy to calculate aggregations, I would emphasize here capabilities like extracting "the 3 most valuable transactions".

  proc sql - as usual

  proc rank - also useful to quickly calculate ranks (overall ranks, or ranks by customer)

I would also suggest a search with the following search keywords: "time series datamining"   - since part of your problem (churn, direct marketing) is more related to this topic.

Enterprise Miner has Time Series nodes: TS Correlation, TS Data Prep, TS Decomp, TS Dimension Reduction, TS Exponential Smoothing, TS Similarity.

If you have EM, those nodes are specifically designed to handle these kind of data and problems.

If you don't have EM, the procedures in SAS/STAT that do predictive modelling: REG, GLM, LOGISTIC, GENMOD, GLMSELECT (and many other).

ets_kps
SAS Employee

If you have time series data on individual customers then you likely have what are known as panel or longitudinal data.  There are several tools within SAS to deal with these.  If you are working with EG there is a menu item for Regression with Panel data. Give that a try.

panelcap.PNG

I just now read the part about not having ETS.  If you don't have ETS, then the EG screenshot shoudn't work.  You can estimate many of the models that PROC PANEL estimates with PROC MIXED but you will need to write some code. 

sas-innovate-2024.png

Join us for SAS Innovate April 16-19 at the Aria in Las Vegas. Bring the team and save big with our group pricing for a limited time only.

Pre-conference courses and tutorials are filling up fast and are always a sellout. Register today to reserve your seat.

 

Register now!

Multiple Linear Regression in SAS

Learn how to run multiple linear regression models with and without interactions, presented by SAS user Alex Chaplin.

Find more tutorials on the SAS Users YouTube channel.

Discussion stats
  • 13 replies
  • 2670 views
  • 3 likes
  • 6 in conversation