Predictive Models

Home/Predictive Models

Customer Churn

2017-09-23T20:21:24+00:00

The purpose of the study was to identify customers at risk of leaving. The research question being tested was: Research Question 1: What is the probability that customers will leave? We built predictive models. We performed churn analyses for the utility industry by analyzing the data including addresses, gas consumption, products, contract terms and [...]

Predicting Advertising Campaign Success

2017-09-22T16:39:36+00:00

The purpose of this study was to predict the success of advertising campaigns by analyzing numerous data sources to determine the ROI of an advertising campaign. (e.g., Reach, Influence). We predicted the success of a particular advertising campaign based on brand, talent, external factors, and trends.  We built predictive models. There is a 90% probability [...]

Forecasting Sales for New Sites

2017-09-22T16:41:24+00:00

The purpose of the study was to forecast sales of new sites based on the data and sales of the operating companies. The hypothesis being tested was: H1: The investments in new companies are getting a high return. We built predictive models. We used location analytics. There is a 72.35% probability that the investments [...]

Sales Prediction Algorithm

2017-09-22T20:53:01+00:00

The purpose of the study was to predict the sales per day for each of the next 100 days. We created a general purpose data science module in python that could Digest the daily sales data for the past 3 years and develop a model Identify and use any publicly available sources of data [...]

Healthcare Paid Claim Data Modeling and Analysis

2017-09-22T21:42:20+00:00

The purpose of the study was to predict the likelihood of a claim being part of an accident. We developed the algorithm that could leverage features, both from the claims and potentially beyond the claims. We inserted an algorithm into our client's existing ETL process and provided a single, key metric:  likelihood of this [...]

Real Estate Forecast Algorithm

2017-09-22T19:31:56+00:00

The purpose of this study was to forecast the sales and leasing revenue derived from non-managed properties for the next six-month period, based on the historical information in the Input data sheet for the previous six months. The hypothesis being tested was: H1: The sales and leasing revenue derived from non-managed properties will improve. [...]

Companies Are at Risk of Losing Their Customers

2017-09-22T19:36:25+00:00

The purpose of this study was to predict whether companies are at risk of losing their customers. The hypothesis being tested was: H1: Companies are at risk of losing their customers. We built predictive models. We performed predictive analytics to test the hypothesis. There is an 87.27% probability that companies are at risk of [...]

Predicting Brexit-like Events Using Big Data

2017-09-22T19:38:01+00:00

The purpose of the study was to develop outlooks on macroeconomics and financial markets based on market indices, market economic indicators and a selection of research papers. We helped our clients incorporate these outlooks in the tactical asset allocation for their own assets. Therefore, they can potentially generate great financial benefits. [...]