MDF Reasonable Cost Model Ideation

Background Information
Market Development Funds (MDF) are monetary funds provided to qualified and authorized customer’s channel partners to subsidize the costs of Marketing and Sales activities that drive demand for customer’s products, services, and solutions.
 
Authorized channel partners send out proposals to our customer. Once the proposals are approved, channel partners can utilize the fund for their marketing purposes and can get full audit of MDF activity, like requesting for fund and claim approval.
 
This entire MDF process for partners has various stages / process similar to the  mentioned below.

• Partner Selection and MDF pre-planning for partner
• Partner activity planning to utilize the MDF
• Execution of activities
• Claim submission
• Claim validation

Contest Problem
The ask from the customer is to build a "reasonable cost model" , to be used, by Team B above in the red circle above, as a guideline during the proposal preparation and submission by the partner. The model should be based upon existing data describing various parameters (Region, market, activity type ..etc) or perhaps something else entirely.
 
The output of the “reasonable cost” model would be either an expected range of proposal costs, a specific cost or both.
 
The challenge in this case, is that while the customer has ample data available for analysis, critical data, such as “proposal rejection reason=Unreasonable/inflated price”, are missing and will not be available.
 
As such, from the community we seek:
 

• Ideas / approach on how to solve the problem
• Proof of idea(s) with white paper explaining the approach, justifying the thought process (e.g. it’s already proven in the market etc), pseudo code, an explanation as to why the approach is realistic and how to measure the success of this model.
• The best submissions will include a proof of concept, i.e a sample algorithm to prove that the solution will work. In the end we would run this algorithm and it should give the required output
• Based on the suggestions and proposals resulting from the ideation, a new challenge (or possibly multiple challenges) will be launched, with particular focus for the creation of a model and/or implementation of the described solution.

As part of the challenge, you will be provided with a sample of the available data. The larger dataset would potentially be used in conjunction with a future contest.
5,000 rows in CSV format available here.
 
Note that, in the sample data provided, all fields referring to names of companies/clients, the real names have been replaced with dummy values to protect the anonymity of the data.
 

Final Submission Guidelines

Submission Contents
A document with details for the proposed algorithm and/or a proof of concept solution, pseudo-code or any documentation/ previous research papers that helps illustrate proposal.
The final submission should be a report, more like a technical paper. It should include, but not limited to, the following contents. The client will judge the feasibility and the quality of your proposed likelihood function.
 
Title : Title of your idea
Abstract / Description :  High level overview / statement of your idea

• Brief reiteration of the problem at hand
• Outline of the approach of the algorithm implementation
• Outline of each functional unit of the algorithm implementation
• Summarized conclusion

Details:

• Detailed description. You must provide details of each function unit and details of how it should be implemented
• Description of the entire model approach to how can you compute the "reasonable cost model" ,
  • What if we want to run this as a Marathon competition?
• If the model is created using the existing data, what will be the ground truth and how to create the same?
• Can we leverage any public sets ? If so, what are those ?
• Prove ideas with white paper (telling why their idea will work, it’s already proven in the market etc) which needs to be realistic
• The advantage of your idea - why it could be better than others
• If your idea includes some theory or known papers;

- - Reason why you chose this apporach
- - Details on how it will be used
- - Reference to the papers of the theory

• Reasonings/obstacles behind the feasibility of your idea
• What is the Ground truth and approach to create the same,
• Pseudo code(or PoC code), and its description

Appendix (optional) :

• Bibliography, A reference to the paper, etc.

 

Format

• A document should be a minimum of 2 pages in PDF / Word format to describe your ideas.
• It should be written in English.
• Leveraging charts, diagrams, and tables to explain your ideas is encouraged from a comprehensive perspective.
   

Checkpoint Submission

In this challenge, we allow checkpoint submissions. In the checkpoint submission, please at least include the “Abstract / Description” part.
The checkpoint submissions will be evaluated at the halfway point of the challenge, and the top five will receive a prize of $100.

Final Submission

In the final submission, you must submit all items described in the Contents section above within the defined time as this is a time critical project. 
 

Judging Criteria

You will be judged on the quality, clarity, completeness of your ideas and their innovative approach. The winner will be chosen by the most logical and convincing reasoning as to how and why the idea presented will meet the objective. Note that, this contest will be judged subjectively by the client and Topcoder. The high-level judging criteria are as follows:

• Feasibility and Completeness of the Idea (60%)
  • Can your solution compute a "reasonable cost model". And can you prove that?
  • Approach for creation of ground truth
  • Considering we may launch a Marathon challenge in few weeks; Does your solution cover how to run a Marathon challenge using the current data or adding more public datasets?
• Ease of implementation (40%)
  • That pseudo code or PoC code is presented
  • The above code Implementation is easier than other submissions

For example, the following will be judged higher

• Having PoC code is better than just pseudo code, but if the pseudocode report has better solution and highly feasible reasonings to accurately calculate the scores, the latter report will be evaluated better.

 
Note: We will be looking mainly at “Abstract / Description” for the checkpoint submissions.