Deloitte’s Data Analytics

Deloitte’s Data Analytics

1. The advent of data analytics

   • distributed file systems
     • For large amounts of data the market standards are platforms like Apache Hadoop
   • Database management
     • Anlaytics need management, and you can use a large variety of data managements programs that already exist like: Oracle
   • Advanced analytics
     • refers to a variety of statistical methods that are used to compute for an event occurring

2. data quality

   • What is the proportion of defaults in the data?
     • Typically in practice, data with less than 5% of defaults are strong modelling challenges.
   • What is the frequency of values in each variable in the data?
     • The variable can be numerical or categorical
   • What is the proportion of outliers in the data?
     • is often the case that outliers are a result of system error.
   • How many missing values are there and what is the reason?
     • missing due to nonresponse, due to drop out of the clients, or due to censoring of the answers, or simply missing at random.

3. Model Development

   • Classification
     • distinguish the good applicants from the bad ones.
   • Reject inference
     • the model is not truly representative for a through-thedoor client. This problem is often termed “reject inference”.
   • Logistic regression
   • Variable selection
   • Information Value

4. Model Performance

   • Goodness of Fit
     • A simple graph would allow us to inspect visually the fit.
   • Predictive Power
     • its ability to generalise the rules it has learned from the training data set to a new (unseen) data set.
   • Confusion Matrix

5. Model refinements

6. Model Interpretation

   • This interprets coefficient B, which helps us understand the rate of change in probability

Bilder und Dateien der Mindmap