Search icone
Search and publish your papers
Our Guarantee
We guarantee quality.
Find out more!

Application of ANN in non-life insurance industry

Or download with : a doc exchange

About the author

 
Level
Expert

About the document

Acepublisher .
Published date
Language
documents in English
Format
pdf
Type
term papers
Pages
12 pages
Level
Expert
Accessed
0 times
Validated by
Committee Oboolo.com
0 Comment
Rate this document
  1. Abstract
  2. Introduction
  3. Literature review
    1. Customer lifetime value (CLV)
    2. Customer lifetime value (CLV) in the insurance industry
  4. Methodology
    1. Scope
    2. Research design
    3. Data mining techniques (DMT) for predicting CLV
    4. Multilayer perceptron
    5. SMOreg
    6. IBK
    7. Meta bagging
  5. Evaluation of the proposed DMT
  6. Proposed algorithm to allocate market Resource
  7. Computational experiment
  8. Simple K-means
  9. Analysis and performance measurement
  10. Conclusions and managerial implications
  11. References

Most of the Institutions are yet to use basic best practices for marketing spending and effectiveness for allocation of marketing resources. They traditionally allocate their marketing budget either based on historical allocation level or based on product level priorities. Marketing has come under increased pressure as the marketing managers are constantly challenged with the problem of how to allocate the limited marketing budget across customers and show return on their marketing spending. As a result, there has been an increased interest and proliferation of work on customer lifetime value (CLV) and efficient allocation of market resource. Hence, prediction of CLV and efficient allocation of marketing resources are critical. In this paper, the successful application of artificial neural network (ANN) algorithm and its usefulness in prediction of CLV is done. The sample data of Business to Business customers from Non-Life Insurance Industry is used for the prediction of CLV. Also the paper compares the ANN with other data mining algorithms for its prediction accuracy.

[...] The paper contributes in terms of providing analytical tools and models to profile the customer segments in to financial portfolio by measuring its value. Customers are the financial assets of the company hence they should be valued and analyzed and profiling has to be done for efficient allocation of resources. In this light, the managers should carefully select the customer profile before they want to target. We clustered the PCLV data set using EM and Simple K-means. Here based on various trials we have arrived at five clusters for applying the clustering algorithm. [...]


[...] Bradlow, and Howard Kunreuther Modeling the "Pseudodeductible in Insurance Claims Decisions, Management Science,? Vol No.8, pp 1258- S.Gupta and D.R.Lehmann, ?Customer as assets, ?Journal of Interactive Marketing,? Vol No.1, pp S.Gupta, D.R.Lehmann and J.A Stuart, ?Valuing customers. Journal of Marketing Research,? Vol No.1, pp Sunil Gupta, Dominique Hanssens, Bruce Hardie, Wiliam Kahn, V. Kumar, Nathaniel Lin, Nalini Ravishanker, and S. Sriram, ?Modeling customer lifetime value,? Journal of Service Research, Vol No.11, pp Sunil Gupta and Thomas J. Steenburgh. "Allocating Marketing Harvard Business School Working Paper,? No.2, pp 08- [10]. [...]


[...] Table 1.2 gives the RAE values corresponding to the number of nodes in the hidden layer. It is found from the data that for Hidden layer 4 with Epochs 1000 and learning rate 0.3 has the minimum RAE of It is also observed that varying the learning rate from 0.4 to it over fits and there is no significant change in RAE. Table 1.2 : Performance of ANN: By varying the Hidden Layer and Epochs. Sl No Description Evaluation Correlation coefficient Mean absolute error Root mean squared error Relative absolute error Root relative squared error H - N - 500 L - H - N - 500 L - H - N - 500 L - H - N - 500 L - H - N - 500 L - H - N - 500 L - Sl No Description Evaluation Correlation coefficient Mean absolute error Root mean squared error Relative absolute error Root relative squared error H - N - 1000 L - H - N -1000 L - H - N -1000 L - H - N -1000 L - H - N -1000 L - H - N -1000 L - V. [...]

Top sold for business strategy

Carlton Polish Co.

 Business & market   |  Business strategy   |  Market study   |  11/18/2011   |   .pdf   |   9 pages

Does competition affect social preferences in the context of a bargaining game? Discuss

 Business & market   |  Business strategy   |  Case study   |  05/21/2012   |   .doc   |   3 pages

Most rated for business strategy

Bank of America

 Business & market   |  Business strategy   |  Presentation   |  07/07/2008   |   .doc   |   17 pages

Benchmarking Vestas against Gamesa wind turbines

 Business & market   |  Business strategy   |  Case study   |  11/15/2012   |   .doc   |   8 pages