Transportation Industry

There are numerous ways in which Business Intelligence Solutions can help you improve your transportation business performance and processes, reduce expenses, decrease the likelihood of personal injuries, increase revenue and gain a competitive edge.

The definition of data mining and detailed characteristics of a data mining project can be found in our white paper “Data Mining: the Means to a Competitive Advantage”.

In order to understand why traditional statistics are not an adequate tool for the vast majority of data-driven transportation industry problems, see our presentation "Data Mining vs. Statistics". 

The essence of our approach is to understand and analyze our client’s business problem and corresponding data through the prism of various statistical/data mining models.  We are always able to produce the best possible model/results and help our clients in the most effective and scientifically sound way.

Traffic Incident Analysis

The development of procedures for incident risk identification, quantification, risk measurement and monitoring. Estimation of employee propensity for personal injury/accident and probability of personal injury/accident. Employee/branch ranking according to personal injury/accident probability. Employee profiling and segmentation according to probability of personal injury/accident. Driver identification of personal injury/accident and development of the program to reduce overall probability of personal injury/accident. Evaluation of the effectiveness of anti-accident program (in particular, disciplinary actions and educational events). 

Accident cause analysis. Impact of transportation engineering factors (traffic management, pavement conditions, road characteristics, etc) and drivers’ behavior (in particular, history of traffic violation) on probability of accident. Classification and rating of accident causes on probability of accident occurrence.

Trend identification and forecasting (monthly, quarterly, yearly, etc.) of:

1.    the number of accidents by category, taking into account seasonality and other factors
2.    the cost of transportation means/system repair induced by accidents 
3.    the number of personal injuries by category due to accidents
4.    the cost of worker compensation due to accidents

GIS analytics/spatial cluster analysis of accident data. Identification and ranking of itineraries/roads with the highest probability of accidents by region.

Development of program/actions to reduce probability of accident.

Customer Relationship Management

Gaining, sharing, expanding, and utilizing customer knowledge.

Customer profiling and customer  segmentation (see our presentation “Cluster analysis vs. Segmentation”) with the usage of demographic, geographic, psychographic and behavioral variables and historical business information.

Data enrichment of the internal customer database with Census and other public/private data (the essence of data enrichment and different sources of external supplementary data for CRM problems are discussed in our presentation "Data Enrichment for CRM" ).

Improving marketing ROI by targeting specific customer segments.
Customer profitability and customer loyalty. Customer acquisition and retention. Churn modeling/customer defection and customer attrition. Customer satisfaction and development of programs to improve customer satisfaction.  Personalized marketing and pricing. Targeted marketing and multichannel management. Optimal (i.e., most profitable) allocation of your marketing funds.

Development of lifelong relationships with your most profitable customers and addressing other CRM challenges such as up-sell and cross-sell (application of bivariate regression to up-sell and cross-sell is described in our white paper “Joint Regression Model for Sales Analysis”).


Route optimization based on various criteria, including time, cost, number of stops and population density in GIS. Travel time analysis and forecasting.
Business site location and service area optimization based on cost in the presence of customers and competitors.
Traffic pattern analysis and forecasting.
Analysis and forecasting of freight transportation demand.