|Insurance||Insurance Subrogation Prediction solution based on PolyAnalyst|
|Fraud||PolyAnalyst Fraud Detection and Investigation capabilities|
|Pharma||PolyAnalyst for Text in Pharma Industry|
|Electronic Data Services||
Employee Survey Analysis Presentation
EDS uses PolyAnalyst to analyze surveys generated by its Human Resources department. The anonymous survey responses include demographic variables, Likert-scale ratings, and open-ended responses. EDS configured the tool to provide results of text analysis along side the traditional quantitative results, examining key issues such as loyalty, productivity, keywords most associated with certain locations and job types, tenure, hot issues and correlations between various topics.
Employee Survey Analysis Case Study
A case study highlighting the results of the analysis of an employee satisfaction survey as a major information technology corporation. The study discusses the value of integrating information gleaned from opened-ended survey questions together with demographic data to identify interesting and revealing correlations.
|International Air Transport Association||
Flight Safety Analysis using STEADES Data
The International Air Transport Association (IATA) incorporates PolyAnalyst into their analytical software to generate reports on key issues mentioned by pilots, crew members and ground staff
Flight Safety Data Analysis
The purpose of the project was to develop new text mining methodologies for the analysis of flight safety data. PolyAnalyst was used for the analysis of de-identified safety data from the Aviation Safety Action Program (ASAP) database of Southwest Airlines, with the ultimate goal of further enhancing long-term flight safety performance.
|GAIN, Airbus, FAA||
Guide to Analytical Methods & Tools for Airline Flight Safety Analysis
An case study demonstrating how PolyAnalyst was used by the FAA (http://www.flightsafety.org) to perform flight safety data analysis by examining the comments submitted by crew and ground personnel.
|A State Medicaid Agency||
Medical Fraud Detection through Data Mining
A state Medicaid agency covering about one million people throughout the state wanted to identify and reduce the number of fraudulent medical transactions. To accomplish the task of fraud detection, the agency hired an IT company specializing in medical billing solutions, which developed business rules for capturing known fraud mechanisms based on their background knowledge. Random, manual screening of the data demonstrated that this system was able to identify about half of the fraudulent transactions. The other half were not covered by the existing business rules. Together with Megaputer, the agency incorporated a PolyAnalyst fraud detection algorithm to attempt to identify the remaining cases without using the known business rules.
|Central Institute of Mathematics in Economy, Moscow||
Maximizing Profit through Automated Trade Decisions
PolyAnalyst was used to analyze the Russian Short Term Government Bonds (STGB) market. The goal of this research was to develop an optimal strategy of capital management in this market, which would provide the maximum profit. The data included all bond issues prices, currency rates fluctuations, and other market indices for each trading session, since the establishment of this market up to the present day. These data have been analyzed with the help of PolyAnalyst, which discovered an algorithm for making a decision of selling or buying various issues of STGB.
|A Semiconductor Manufacturing Company||
Improving Quality for Automated Manufacturing
A semiconductor manufacturer wants to uncover the root causes attributed to high defect rates in certain production lots. The challenge is to quickly bring up the yield rate into acceptable range for mass production and drive continuous enhancement in order to improve quality and lower cost. The manufacturer needs a powerful analytical tool to pinpoint the most susceptible causal relationships in engineering data.
Direct Marketing: Response Modeling
A national communication services provider was introducing new services. The client was seeking a solution that could learn from the input of marketing, sales and engineering activities, predict geographical areas of high demand and identify the best individual target customers. The client needed a tool to determine the best metropolitan areas to offer their services and the number of customers likely to select various services within each market. Later the same tool was to be capable of driving, tracking, and learning from the marketing effort, and changing the national strategy if necessary. Since there was no available history on a new product, a population with demonstrated pent up demand was identified and then modeled with the help of PolyAnalyst to generate customer profiles.
|Cambridge Technology Partners||
Modeling Propensity to Purchase
The goal of the CTP analysis was to determine how likely a customer would purchase a specific product, given the knowledge of what other items are already in this customer's "shopping basket". We need to find the percentage chance of purchasing this specific additional product. In addition, measures of statistical significance needed to be calculated to make sure that these percentages were greater than random chance. Finally, the most significant rules needed to be extracted. Meaningful conclusions were found in the data, and these are provided after a description of the analysis.
|A Police Department||
Text Mining Crime Reports
Megaputer Intelligence carried out an incident reports analysis project to demonstrate a complete analytical solution for processing a mix of structured data and text in incident reports. This case study discusses a methodology and sample results of discovering knowledge hidden in unstructured data. The project was carried out with the help of the data and text mining system PolyAnalyst. An overall objective was to create an analytical solution that investigators can routinely use to identify new patterns and associations between types of incidents, locations, time and descriptive details of the incident. The developed approach consists of a series of steps: preprocess data to the format suitable for further analysis, extract important concepts and terms through text-mining, analyze patterns and co-occurrences of identified concept, and finally develop an automated solution for crime pattern analysis.
Text Mining for Public Input Analysis
Text mining for public input analysis in a government agency.
Introduction to Call Center Data Analysis
An introduction to how the PolyAnalyst software package can be used to assist in the analysis and automated categorization of customer to agent dialogs stored in a database.
Analysis of automobile accident reports
Presentation of results of analyzing types of automobile accidents and the conditions in which they occur.
Customer Satisfaction Survey Analysis
Presentation of the results of a survey analysis project for a major hotel chain.
|© Megaputer Intelligence, Inc. All Rights Reserved. Legal & Privacy Information|