#Indication and Identification of Supplier Performance
The Project is built for SIRIONLABS HACKFest in hackerearth
Project Overview
Supplier performance management (SPM) is a business practice that is used to measure, analyze, and manage the performance of a supplier. Supplier management professionals seek to cut costs, alleviate risks, and drive continuous improvement. Companies use systems to monitor supplier performance levels
Suppliers to Focus On: High Value and Strategic Suppliers
The important factor that should influence the choice of evaluation methodology includes the type of suppliers that a company has. In the supplier performance management program, it is important for company personnel to focus on the higher value and more strategic suppliers since these suppliers contribute the greatest amount of risks. It often doesn’t make economic sense to include low dollar value, one time business, or non-strategic suppliers in this type of program. By grouping these top suppliers together and examining the company’s relationships with them, some common attributes will become evident. These attributes of the relationship can be used to develop the areas and metrics with which to measure.
Problem Statement
Identified as to Design and Develop a Machine Learning system to Selecting a supplier from among thousands and doing a predictive performance analysis is a challenge which most of the client's face. Evaluating supplier performance based on multiple attributes would not only help clients mitigate risk but also help reduce costs.
In order to achieve the same, we have provided some unstructured supplier performance data which may be millions of records, with multi-dimensional attributes from supplier rating, region, cost etc.
Supplier performance can be defined as follows:
Formula using attributes. For example, Minimize [Cost] + Maximize[Rating] for upcoming year based on the historical data which can be executed within a specific duration [e.g., 30 days] for a specific service [e.g., Application Development] with minimum escalation
As the expected outcome is meant for the future, all the numerical fields should be based on predictive computation as per historical data for each supplier.
Sample data set -
{
"Supplier Name": "Genpact",
"Region": "North America",
"Country”: “United States”,
"Function": "Consulting",
"Service": "Applications Development & Maintenance",
"Avg. Cost($)": "150k",
"Rating": 80,
“Average Delivery Time”: "180",
“Number of Escalations”: "40",
“Year”: "2017"
“Resources”: "6000"
}
Tagline Sustainable Innovation Needs Actionable Insights
Project Objective
The Intent and Motive of Project is to Making things easier for shopkeepers deals with price recommendation for marketplace sellers. One of the biggest promises of in selecting machine learning is to automate decision making in a multitude of domains. At the core of many data-driven personalized decision scenarios is the estimation of heterogeneous treatment effects: what is the causal effect of an intervention on an outcome of interest for a sample with a particular set of features?
Such questions arise frequently in customer segmentation in details as follows what is the effect of placing a customer in a tier over another tier, dynamic pricing what is the effect of a pricing policy on demand and In many such settings we have an abundance of observational data,
Example Applications
Customer Targeting
Businesses offer personalized incentives to customers to increase sales and level of engagement. Any such personalized intervention corresponds to a monetary investment and the main question that business analytics are called to answer is: what is the return on investment? Analyzing the ROI is inherently a treatment effect question: what was the effect of any investment on a customer's spend? Understanding how ROI varies across customers can enable more targeted investment policies and increased ROI via better targeting.
Personalized Pricing
Personalized discounts have are widespread in the digital economy. To set the optimal personalized discount policy a business needs to understand what is the effect of a drop in price on the demand of a customer for a product as a function of customer characteristics. The estimation of such personalized demand elasticities can also be phrased in the language of heterogeneous treatment effects, where the treatment is the price on the demand as a function of observable features of the customer.
Problem Solves
In large business firms the major aspect to deal with is the large amount of data, many times the data is unorganized and often hard to interpret.One such aspect is "feedback from the customer"
To bring in the perspective, the issues can be: Understanding weather the user is happy with a product or are they facing some technical bugs which interupts their work flow. Issues faced by the users Manytimes same issues are faced by multiple users.
Technology Stack
Machine Learning ,Python,ARIMA MODEL,Data Visualization