HDD Performance Testing:

The Problem Statement:

The problem can be characterized as one of detecting rare events from a time series of noisy and nonparametrically-distributed attributes. Currently, the Customer is using a threshold algorithm which triggers a SMART flag when any single attribute exceeds a predefined value. These thresholds are set conservatively to avoid false alarms at the expense of predictive accuracy, with an acceptable false alarm rate on the order of 0.1% per year (that is, one drive in 1000). For the SMART algorithm currently implemented in drives, the Customer estimates the failure detection rate to be 3-10%.

The Solution:

The process of feature selection includes not only deciding which attributes to use in the classifier, but also the number of time samples, used to make each decision, and whether to perform a Pre-processing transformation on these input time series. Some of the attributes are not strongly correlated with future drive failures and including these attributes can have a negative impact on classifier performance.

As it is computationally expensive to try all combinations of attribute values, we are using the fast-nonparametric reverse-arrangements test and attribute z-scores within Decision Sciences Factor (DSF) to identify potentially useful failure identification algorithms.


DSF can significantly improve the current performance of the hard drive failure prediction algorithms.

Increased accuracy of detection, benefitting users to back up their data.

DSF Insights gained, can be used in other areas where rare events must be forecast from noisy, nonparametric time series, such as in the prediction of rare diseases, electronic and mechanical device failures etc.


The Analytical Revolution Of Sensors

Speaking during Question Hour in the upper house of Indian parliament on Thursday 11-June-2015, Union Minister of State for Power Piyush Goyal claimed that electricity was available at zero rupees per unit at the Power Grid’s Monitoring Office. When there are continuous power cuts across so many cities and only a few hours of power supply at majority of villages, this actually is a good indicator towards the unbalanced demand/supply situation.


The Search Disruption

There are two specific events which mark this decade, first one being the emergence of disruptive business models such as e-commerce models for retail, travel, transport and services and the second one is the emergence of disruptive technologies such as search and analytics technologies. Both of these events present a series of opportunities in terms of doing cheaper business with faster implementation times, while at the same time they possess a serious threat to the old business models and software licensing models.