Financial institutions provide services such as loans and lease. If a consumer defaults on a loan and fails to pay back the loan amount, financial institution suffers a loss. Hence, it is pivotal for financial institutions to assess the risk of non-payment at the time of application. Utilizing state of the art techniques, like wide and deep model by Google, we develop a data-driven model which provides information on the…
Read more
At the time of purchase of a financial product, there are often a large number of financial products to choose from with subtle differences. Customers often have insufficient knowledge and often end up making a sub-optimal purchase. A model developed by CACTuS ingests initial choice of financial product by the customer and lists closely related products which are financially feasible for the customer and are also likely to derive greater…
Read moreReselling focuses on identifying customers from the current pool of customers who may return again. For example, in car leasing customers often return for a new lease once and when the current lease expires. As it is generally easier to retain your current customers rather than attracting new customers, companies often want to target their current customer base to ensure that customers return to their company for a new contract…
Read more
During the length of a financial contract such as a loan or a lease, a customer is expected to make per-decided frequent payments to the finance company. Late payments or no payments count as losses towards the finance company. A machine learning based solution developed by CACTuS forecasts customer payment behaviour, helping the finance company per-adjust and also suggests an optimal strategy to follow to ensure that customer makes payments…
Read moreThis project seeks to automate tasks that the human visual system can do such as acquiring, processing, analysing and understanding digital images. Given one or typically more images of a scene, or a video, scene reconstruction aims at computing a 3D model of the scene. In the simplest case the model can be a set of 3D points. More sophisticated methods produce a complete 3D surface model. The advent of…
Read more
Root cause analysis (RCA) is a method of problem solving used for identifying the root causes of faults or problems. RCA is widely used in industrial process control, IT operations, health industry and accident analysis in aviation, nuclear plants and rail transport. Without delving in the intricate details of specific problems, several general conditions can make RCA more difficult than it may appear at first sight. It is generally not…
Read moreWhy Predictive Maintenance is needed? Maintenance and reliability professionals in the manufacturing industry face a number of challenges, but the goal of any maintenance organization is always the same i.e. to maximize equipment availability. In order to achieve maximum availability, run-to-failure maintenance suggests that the equipment must be kept running until it fails. However, this strategy may result in catastrophic machine damage as components begin to vibrate excessively, overheat and…
Read more
Semiconductor manufacturing is a complex process with hundred of subprocesses. Different sensors record?diverse information including the profiles of tools used in each fabrication subprocess, temperatures, pressures, etc. The output of this process is a semiconductor wafer. Any malfunctioning subprocess can introduce a yield loss in the output wafer and hence render the entire batch useless resulting in potentially millions of dollars of loss. It is therefore imperative to identify the…
Read moreAlmost all kind of engineering industrial process and production is performed by rotating machinery like motors, pumps, gearbox, fans, and assembly lines, etc. The condition-based monitoring of these types of equipment helps to boost productivity and profitability. In recent years, the industry has moved steadily from reactive to predictive long-term maintenance. The vibration signals are processed using advanced signal processing algorithms, machine learning/deep learning tools to diagnose the incipient fault…
Read more
Innovative fault prediction can play a crucial role in ensuring smooth and cost effective process management. In this project, we designed a solution for predicting failure events by leveraging modern bleeding edge AI techniques such as deep learning, meta-learning, Bayesian optimization etc. Using AI we were able to successfully predict process/plant faults from telemetric data. Furthermore, correctly predicting the probability of failure events in the near future can serve as…
Read moreToday, the industry is outtted with robots, cameras and several kinds of other sensors that collectively perform picking, packing and transferring packages with no human presence or oversight. Without this, if 500 workers are required in a factory instead, only ve technicians would be required to service the machines and keep them working. As industrial technology grows increasingly pervasive, this wave of automation and digitization is being labelled Industry 4.0, …
Read more
Root cause analysis (RCA) is a method of problem solving used for identifying the root causes of faults or problems. RCA is widely used in industrial process control, IT operations, health industry and accident analysis in aviation, nuclear plants and rail transport. Without delving in the intricate details of specic problems, several general conditions can make RCA more dicult than it may appear at rst sight. It is generally not…
Read moreInnovative fault prediction can play a crucial role in ensuring smooth and cost eective process management. In this project, we designed a solution for predicting failure events by leveraging modern bleeding edge AI techniques such as deep learning, meta-learning, Bayesian optimization etc. Using AI we were able to successfully predict process/plant faults from telemetric data. Furthermore, correctly predicting the probability of failure events in the near future can serve as…
Read more
Almost all kind of engineering industrial process and production is performed by rotating machinery like motors, pumps, gearbox, fans, and assembly lines, etc. The condition-based monitoring of these types of equipment helps to boost productivity and protability. In recent years, the industry has moved steadily from reactive to predictive long-term maintenance. The vibration signals are processed using DSP, machine learning/deep learning tools to diagnose the incipient fault as well as…
Read moreSemiconductor manufacturing is a complex process with hundred of subprocesses. Different sensors record diverse information including the profiles of tools used in each fabrication subprocess, temperatures, pressures, etc. The output of this process is a semiconductor wafer. Any malfunctioning subprocess can?introduce a yield loss in the output wafer and hence render the entire batch useless resulting in potentially millions of dollars of loss. It is therefore imperative to identify the…
Read more
Accurate failure time estimation of mechanical components plays a signicant role in enhancing the reliability of the machines. Ball-bearing failures are the most probable failures in the industrial rotating machinery. Therefore, predicting the remaining useful life of ball bearing proves to be helpful for maintenance scheduling. In data driven methods for prognostics, the remaining useful lifetime is predicted based on a health indicator. The health indicator detects the condition of…
Read more