Featured
Concept drift: A Challenge in predictive analytics

Concept drift: A Challenge in predictive analytics

What is concept drift? In predictive analytics, machine learning, and incremental learning the concept drift is an event that occurs when the statistical properties of the output parameter, which the model is trying to forecast, alters over time in unexpected behaviors. This results in glitches because the forecasts become less correct as time passes. In stream data mining, where input data arrives based on time instance this issue is prominent. In other words, online learning suffers most from concept drift problem. Let…

Read More Read More

Predictive Collision Avoidance in Connected Car Industry

Predictive Collision Avoidance in Connected Car Industry

Predictive Collision Avoidance in Connected Cars Technology proposes drivers many features in ADAS (Advanced Driver Assistance Systems) and AD (Autonomous Driving AKA Driverless car) developments.  Among them, perhaps, predictive collision avoidance system is most cherished. With progressive sensors, big and fast data, and car-to-car connectivity, predictive analytics technology solutions will one day come to zero auto accidents. Before proceeding to read further, make sure you have read introduction and details of predictive analytics in connected car industry in this post….

Read More Read More

Predictive Analytics in Connected Car Industry

Predictive Analytics in Connected Car Industry

Introduction to Predictive Analytics in Connected Car Industry Imagine the flawless automobile vehicle ever, like autonomous car. It exercises itself on the street even when you are having a nap, halts itself at your favorite hotel for your favorite cuisine, and awakens you just in time for a rapid touch-up before you step out of the car. If this is the matter from a science fiction film, it is coming to real life one-step at a time. Connected car industry…

Read More Read More

Automotive Industry Analytics

Automotive Industry Analytics

Introduction to Automotive Industry AnalyticsNowadays, vehicles can produce and collect huge amount of raw data for automated analysis. Cars can have minimum 50 sensors, maybe more than that, specially intended to gather complete facts like speed, driving performance, emissions, distance, resource usage and fuel consumption. When merged with a classy predictive analytics resolution, data scientists and analysts can convert raw unfiltered data into meaningful information. This information can they be used in decision making processes in public and private sectors….

Read More Read More

Ensemble Technique: Solution to complex problems in Predictive analytics

Ensemble Technique: Solution to complex problems in Predictive analytics

What is Ensemble technique ? As discussed in previous few posts about predictive analytics challenges, Ensemble technique is a solution for most of them. Incremental learning environment, specifically demands for ensemble based algorithms for problem solving due to dynamic data generation functions. Ensemble technique is a class of meta-algorithms that merge various machine learning algorithms into single predictive model in order to reduce variance (bagging), bias (boosting), or increase predictions quality. Let us see a real world example to understand what ensemble technique exactly does….

Read More Read More

Missing Features: A challenge in data preparation

Missing Features: A challenge in data preparation

What is Missing Features Problem? The principle of machine learning and AI based application is “Garbage in-garbage out”. Hence, data cleaning and Exploratory Data Analysis are the key steps of data preparation phase. In the real world, the data comes with noise. The noise may include many things such as incorrect data, unnecessary extra data, missing values, missing attributes/features. Among st them, it is difficult to handle missing features problem. Missing features is one of the most common problems that…

Read More Read More