Aly Megahed

Modeling Business Insights into Predictive Analytics for the Outcome of IT Service Contracts

The chances of winning highly valued Information Technology (IT) service contracts are influenced by various factors. Identifying key factors driving the competition and the early prediction of the outcome (either winning or losing such sales opportunities) can have significant business benefits. Given the complexity of IT services, range of potential attributes, and scarcity of comparable data sets, the straightforward approach of developing predictive analytical models that works well in other industries, such as consumer products, tends to achieve lower accuracy in this context. In this paper, we develop an approach that uses business insights and domain knowledge in the classification of several of the attributes influencing the outcome. We show how using this approach in a naïve Bayes predictive analytics framework can vastly improve the prediction accuracy. Further, we discuss two applications of our model, early prioritization of newly validated sales opportunities and optimization of sales force allocation and planning.

Pricing IT Services Deals: A More Agile Top-Down Approach

Information technology service providers bid on high valued services deals in a competitive environment. To price these deals, the traditional bottom up approach is to prepare a complete solution, i.e., know the detailed services to be offered to the client, find the exact costs of these services, and then add a gross profit to reach the bidding price. This is a very time consuming and resource intensive process. There is a business need to get quick (agile) early estimates of both cost and price using a core set of high level data for the deal. In this paper, we develop a two-step top down approach for doing this. In the first step, we mine historical and market data to come up with estimates on the cost and price. We provide some numerical results based on industry data that statistically shows that there is a benefit of using historical data in this step beside the traditional way of using market data. Because the bidding price is not the sole factor affecting the chances of winning a deal, we then enter the different price points in a predictive analytics model (step two) to calculate the relative probability of winning the deal at each point. Such probabilities with the corresponding prices can provide significant insights to the business helping them reach quick reliable pricing.

A Progress Advisor for IT Service Engagements

Monitoring the status of ongoing sales opportunities in IT service engagements is important for sales teams to improve the win rate of deals. Existing approaches aim at predicting the final outcome, i.e., The eventual chance of winning or losing a deal, given a snapshot of the deal data. While this type of prediction indirectly advises on the deal status, it offers limited guidance and insights. During the engagement progress, there occur numerous milestones and key events whose occurrence and status is important in achieving the desired outcome of the deal. These interim milestones and events may happen in different time intervals during the lifecycle of a deal, depending on the deal size and other parameters. In this paper, we describe a novel Bernoulli-Dirichlet predictive model for predicting the occurrence of key events and milestones within a service engagement process to assist in monitoring the progress of ongoing deals. This model enables predicting the timeline and status of the next event(s), given the current history of milestones activity in the engagement lifecycle. Through such a step-by-step guidance, sales teams may have a higher chance of success by knowing of upcoming events, and preparing to counter undesired events. We show the empirical evidences of significance and impact of such an approach in a real-world service provider environment.

A Top-Down Pricing Algorithm for IT Service Contracts Using Lower Level Service Data

Information technology (IT) service providers competing for high valued contracts need to produce a compelling proposal with competitive price. The traditional approach to pricing IT service deals, which builds up the bottom-up costs from the hierarchy of services, is often time consuming, resource intensive, and only available late as it requires granular information of a solution. Recent work on top-down pricing approach enables efficient and early estimates of cost and prices using high level services to overcome and complement these problems. In this paper, we describe an extended pricing method for top-down pricing using the secondary service level. The method makes use of data lower level services to calculate improved estimates, yet still requires minimal input. We compare the previous and new approaches based on industrial data on historical and market deals, and demonstrate that the new approach can generate more accurate estimates. In addition, we also show that mining historical data would yield more accurate estimation than using market data for services, experimental results are in consistent with our findings in previous work.

An Optimization Approach for Adaptive Monitoring in IoT Environments

In Internet of Things (IoT) environments, there are multiple sensors and devices monitoring different metrics and producing massive amounts of data. Monitoring of metrics can be done at different frequencies. Systems and applications that consume monitoring data typically use constrained IT resources, e.g., constrained network facilities, storage, display, processing/computing power, and energy. Given the limited quantity of resources used by these monitoring systems and applications, it is impossible to be able to collect data of all metrics in the application’s context with a very high monitoring frequency. Additionally, changes in the IoT environmental context may affect the choice of metrics that should be monitored and their monitoring frequencies. To address these issues, we propose in this paper a novel approach based on optimization model to optimally determine the metrics that should be monitored and the frequencies at which these metrics are to be monitored. Our approach is an adaptive iterative approach in which the metric frequencies are re-optimized whenever an environmental event or a monitored metric value triggers the need for such re-optimization. We also present a proof-of-concept implementation of our approach that shows the efficiency of adopting it.

Optimal assignment of autonomic managers to cloud resources

There has been an increasing number of companies moving towards cloud computing due to its economic model based on the so-called pay-as-you-go. The cloud is known as a dynamic and scalable environment. These characteristics make the management of this environment a complex task. Using autonomic management potentially helps to solve the complexity of managing large number of provisioned cloud resources. Since using one autonomic manager (AM) might result on inefficiency in the management of the system, we propose in this paper to use a decentralized approach for autonomic management. The problem that we are solving herein is to determine how many AMs to use in order to maximize the performance of the management and minimize the cost of the used AMs. We propose a mathematical model that allows to determine the optimal assignment of resources and AMs in different availability zones taking into account the different costs of the involved AMs as well as the communication overhead. We also give an overview of the implementation of the proposed mathematical model.

A Recommendation System for Proactive Health Monitoring Using IoT and Wearable Technologies

Proactive monitoring of ones health could avoid serious diseases as well as better maintain the individuals well-being. In todays Internet of Things (IoT) world, there has been numerous wearable technological devices to monitor/measure different health attributes. With the increasing number of attributes and wearables, it becomes unclear to individuals which ones they should be using. The aim of this paper is to provide a novel recommendation engine for personalized advised wearables and IoT solutions for any given individual. The way the engine works is through first identifying the diseases that this person is at risk of, given his/her attributes and medical history. This is done via analyzing the individuals unstructured medical history using text mining, adding it to his/her structured demographic attributes, and then feeding this data to a machine learning classification model that predicts eventual diseases. Then, we map these diseases to the attributes that need to be measured in order to monitor them. Lastly, we use a mathematical optimization model that we developed to recommend the optimal wearable devices and IoT solutions for the individual. Thus, our solution enables proactive health monitoring and can thus provide a significant human benefit.

A Discrete Constraint-Based Method for Pipeline Build-Up Aware Services Sales Forecasting

Services organizations maintain a pipeline of sales opportunities with different maturity level (belonging to progressive sales stages), lifespan (time to close) and contract values at any time point. As time goes, some opportunities close (contract signed, or lost) and new opportunities are added to the pipeline. Accurate forecasting of contract signing by the end of a time period (e.g., quarterly) is highly desirable to make appropriate sales activity management with respect to the projected revenue. While the problem of sales forecasting has been investigated in general, two specific aspects of sales engagement for services organizations, which entail additional complexity, have not been thoroughly investigated: (i) capturing the growth trend of current pipeline, and (ii) incorporating current pipeline build-up in updating the prediction model. We formulate these two issues as a dynamic curve-fitting problem in which we build a sales forecasting model by balancing the effect of current pipeline data and the model trained based on historical data. There are two challenges in doing so, (i) how to mathematically define such a balance and (ii) how to dynamically update the balance as more new data become available. To address these two issues, we propose a novel discrete-constraint method (DCM). It achieves the balance via fixing the value of certain model parameters and applying a leave-one-out algorithm to determine an optimal free parameter number. By conducting experiments on real business data, we demonstrate the superiority of DCM in sales pipeline forecasting.

Top-Down Pricing of IT Services Deals with Recommendation for Missing Values of Historical and Market Data

In order for an Information Technology (IT) service provider to respond to a client’s request for proposals of a complex IT services deal, they need to prepare a solution and enter a competitive bidding process. A critical factor in this solution is the pricing of various services in the deal. The traditional way of pricing such deals has been the so-called bottom-up approach, in which all services are priced from the lowest level up to the highest one. A previously proposed more efficient approach and its enhancement aimed at automating the pricing by data mining historical and market deals. However, when mining such deals, some of the services of the deal to be priced might not exist in them. In this paper, we propose a method that deals with this issue of incomplete data via modeling the problem as a machine learning recommender system. We embed our system in the previously developed method and statistically show that doing so could yield significantly more accurate results. In addition, using our method provides a complete set of historical data that can be used to provide various analytics and insights to the business.

An Optimization Approach to Services Sales Forecasting in a Multi-staged Sales Pipeline.

Services organization manage a pipeline of sales opportunities with variable enterprise sales engagement lifespan, maturity levels (belonging to progressive sales stages), and contract values at any given point in time. Accurate forecasting of contract signings by the end of a time period (e.g., a quarter) is a desire for many services organizations in order to get an accurate projection of incoming revenues, and to provide support for delivery planning, resource allocation, budgeting, and effective sales opportunity management. While the problem of sales forecasting has been investigated in its generic context, sales forecasting for services organizations entails the consideration of additional complexities, which has not been thoroughly investigated: (i) considering opportunities in multi-staged sales pipeline, which means providing stage-specific treatment of sales opportunities in each group, and (ii) using the information of the current pipeline build-up, as well as the projection of the pipeline growth over the remaining time period before the end of the target time period in order to make predictions. In this paper, we formulate this problem, considering the service-specific context, as a machine learning problem over the set of historical services sales data. We introduce a novel optimization approach for finding the optimized weights of a sales forecasting function. The objective value of our optimization model minimizes the average error rates for predicting sales based on two factors of conversion rates and growth factors for any given point in time in a sales period over historical data. Our model also optimally determines the number of historical periods that should be used in the machine learning framework to predict the future revenue. We have evaluated the presented method, and the results demonstrate superior performance (in terms of absolute and relative errors) compared to a baseline state of the art method.