We take a holistic approach towards Artificial Intelligence and Data Science and leave no stone unturned to ensure customer success.

Artificial Intelligence Disciplines
Artificial Intelligence Disciplines

We have endeavoured to accumulate multidisciplinary skill sets required to deliver customer solutions through our panel of subject matter experts and researchers.

Data-driven Solutions

Our data scientists and subject matter experts work together to deliver data-driven solutions and consulting for a variety of industry verticals and business functions.

Customer Experience & Lovability

Sculpt customer happiness and avoid churn by employing deep learning on customer behavior and feedback data. Make your brand go viral by making it lovable.

Learn More
Personalisation & Automation

Anticipate the need before it is needed. Make just the right offers to only the right customers at the perfect time. Sit back and watch your revenues maximize.

Learn More
Segmentation & Graph Analysis

Know your customers better than they know themselves. Go beyond traditional demographics and psychometrics; use social graphs to build highly responsive audiences.

Learn More
Cognitive Applications

Build bots with humanly emotions and language capabilities. Optimise your customer support operations and make savings which are better spent somewhere else.

Learn More
Risk Assurance & Forensics

Identify irregularities and counter threats before they have taken a toll. We help you recognize patterns to prevent fraud, service abuse, hacking and intrusion.

Learn More
Intelligence & Law Enforcement

Go beyond best effort, correlate data from several sources and dimensions; and identify threats and persons of interest before they have found the opportunity to strike.

Learn More
Intelligent Demand Management

Minimize the costs of inventory, mitigate risks and maximize availability & revenues with advanced predictive analytics. Identify demand patterns and don't let any opportunity pass.

Learn More
Big Data Engineering

Transform into a data-centric organization by building meta data and data pipelines for transformation and storage. Employ architectures which will support use cases of tomorrow.

Learn More

We partner with the technology leaders and industry experts to deliver solutions.

SAS IBM Hortonworks

Research & In-house Tech

We analyze the challenges in-depth and come up with original solutions. We have home grown technology assets and we routinely publish papers in leading journals.

You can view demos of our assets here.

Semantic Text Analytics

STA extracts structured insights from unstructured textual data. This is done through Text Cleansing and Feature Extraction (TCFE), Natural Language Processing (NLP), and Post-processing.

Cognitive Virtual Agent

CVA combines the power of natural language understanding, machine learning, structured data, and business process flow to interact with users through mobile or web.

Social Graph Analytics

SGA identifies connections between the customers and categorizes the nature of connection to build social graph and micro segments for targetting and personalisation.

Intelligent Call Routing

ICR applies descriptive, predictive and prescriptive analytical techniques on psychographic and demographic data of customers and support agent to find the ideal mapping between them.

Automatic Machine Learning

AML eases the task of selecting the right algorithms to solve a problem by using meta-learning to automatically recommend the most appropriate algorithm for a dataset.

Deep Image Analysis

DIA uses deep learning and transfer learning to accuratly classify an image by reducing a pre-trained model on a new domain, thus enabling quick deployments.

Cross-domain Meta-learning for Time-series Forecasting

In this paper, we are investigating in what situations use of additional data can improve performance of a Meta-learning system, with focus on cross-domain transfer of Meta-knowledge.

Read More
Cognitive Computing to Optimize IT Services

In this paper, the challenges of maintaining a healthy IT operational environment have been addressed by proactively analyzing Service Desk tickets, customer satisfaction surveys and social media data.

Read More
Customer Churn Prediction, Segmentation and Fraud Detection in Telecommunication Industry

This work uses social network analysis to extracts relationships between different subscribers to improve the results produced by the traditional learning algorithms at individual subscriber level.

Read More
Intelligent Call Routing to Optimize Contact Center Throughput

This paper proposes that descriptive, predictive and prescriptive analytics can be applied to psychographic and demographic data; to find the ideal mapping between customer and the agent.

Read More
Automatic Diacritization for Urdu

Diacritics are optional and usually not represented in Urdu orthography which can create problems for computational systems. In this paper, a Hidden Markov Model approach for automatic Urdu diacritization is used to disambiguate Urdu text.

Read More
Urdu Text Classification

This paper compares statistical techniques for text classification using Naïve Bayes and Support Vector Machines, in context of Urdu language. Empirical results show that Support Vector Machines outperform Naïve Bayes in terms of accuracy.

Read More
English-to-Urdu Transliteration

This paper describes English to Urdu transliteration system. The mapping rules to generate Urdu text from English transcription and syllabification and Urduization phase is described and finally the issues related to Out-Of-Vocabulary are discussed.

Read More

We love open source and we use it extensively both for our research and customer solutions.

Tensorflow OpenML R Statistical Language Hadoop Apache Spark Apache Storm Elasticsearch, Kibana

Learning & Training

We deliver in-depth courses & training with an emphasis on real world applications. We offer the courses to businesses as well as academically through our learning partners.

Introduction to Data Science

Data Science promises so much to the organisations that they embrace it as essential element of their strategy. This course will help you develop the strategic understanding of Data Science and Applied Knowledge you need to seize the economic, social and business potential of data.

This course will help to develop comprehensive and practical understanding of Data Science. Theory and hands-on labs emphasize on developing your knowledge of Data Science concepts, practices, models, lifecycle, visualisation, platforms and modelling languages (statistics and machine learning) required for you to become advanced beginner in the area of data science. Develop the competence in finding, manipulating, managing, and interpreting data to communicate and operationalize results and insights.

  • Introduction
  • Data Science Lifecycle
  • Statistical and Probability
  • Statistical Computing Language - R
  • Visualization
  • Machine Learning
  • Statistical Pattern Recognition
  • Prescriptive Analysis
  • Python Programming Language
  • Natural Language Processing
  • Information Retrieval
  • Big Data
  • Lab
  • Project
Machine Learning

Machine learning studies the question “how can we build computer programs that automatically improve their performance through experience?” This includes learning to perform many types of tasks based on many types of experience. It is a fast-moving field of computer science with many recent applications within the sciences and medicine.

It is an introductory course which gives an overview of many concepts, techniques, and algorithms in machine learning, beginning with topics such as classification and linear regression and ending up with more recent topics such as boosting, support vector machines, and Bayesian networks.

  • Introduction
  • Supervised Learning
  • Bayesian Decision Theory
  • Parametric Methods
  • Multivariate Methods
  • Dimensionality Reduction
  • Clustering
  • Nonparametric Methods
  • Decision Trees
  • Linear Discrimination
  • Multilayer Perceptrons
  • Local Models
  • Kernel Machines
  • Bayesian Estimation
  • Graphical Models
  • Lab
  • Project
Deep Learning

Deep Neural Networks are increasingly taking over all Artificial Intelligence tasks, ranging from language understanding, and speech and image recognition, to machine translation, planning, and even game playing and autonomous driving. Deep learning discovers intricate structure in large datasets by building distributed representations, either via supervised, unsupervised or reinforcement learning.

This course will cover the basics of deep neural networks, and their applications to various AI tasks. Also fundamentals and contemporary usage of the Tensorflow library for deep learning research will be covered. Tensorflow will be used to build models of different complexity, from simple linear/logistic regression to convolutional neural network and recurrent neural networks with LSTM to solve tasks such as word embedding, translation, optical character recognition.

  • Introduction
  • Feedforward neural networks
  • Backpropagation
  • Regularization
  • Convolution
  • Convolutional neural networks
  • Factor analysis
  • Autoencoder and DBM
  • Recurrent neural networks
  • Natural language processing
  • Lab
  • Project
Cognitive Computing

Cognitive computing refers to systems that learn at scale, reason with purpose and interact with humans naturally. Rather than being explicitly programmed, they learn and reason from their interactions with us and from their experiences with their environment. Those systems have been deterministic; cognitive systems are probabilistic. They generate not just answers to numerical problems, but hypotheses, reasoned arguments and recommendations about more complex — and meaningful — bodies of data.

The success of cognitive computing will not be measured by Turing tests or a computer’s ability to mimic humans. It will be measured in more practical ways, like return on investment, new market opportunities, diseases cured and lives save. This course covers background concepts needed to understand and work with cognitive technologies.

  • Introduction
  • Deep QA Architecture
  • Semantic Integration and Machine Learning
  • Natural Language Processing
  • UIMA
  • Structured Knowledge
  • Domain Adaptation
  • Distributional Semantics
  • Lab
  • Project
Statistical Natural Language Processing

Natural language processing can make sense of the 80 percent of the world’s data that computer scientists call unstructured. This enables them to keep pace with the volume, complexity and unpredictability of information and systems in the modern world.

This course will explore statistical, model-based approaches to natural language processing. There will be a focus on corpus-driven methods that make use of supervised and unsupervised machine learning approaches and algorithms. Also some of the core tasks in natural language processing will be examined, starting with simple word-based models for text classification and building up to rich, structured models for syntactic parsing and machine translation.

  • Introduction
  • Corpora
  • Scripts
  • Encoding and Processing
  • Normalization and Collation
  • Tokenization and Word Segmentation
  • Words
  • Morphology and Finite State Transducers
  • Probabilistic Modelling and Spelling
  • N-Grams
  • Phrases
  • Word classes and POS tagging
  • Rule-Based and Probabilistic Parsing of CFGs
  • Annotated Grammars and Lexical Functional Grammar
  • Hidden Markov Models
  • Meaning and Pragmatics
  • Lab
  • Project
Big Data Analysis using Spark

Hadoop becomes the core component of distributed massive data processing - as necessary to understanding your information as servers are to storing it. This course provides introduction to Hadoop, its file system (HDFS), its processing engine (MapReduce), and its many libraries and programming tools.

Spark has been taking the big-data world by storm after showing consistent benchmarks that boast of it being up to a hundred times faster than traditional architecture - Map-Reduce. This course will attempt to articulate the expected output of Data Scientists and using Spark how to deliver against these expectations. The course assignments include Log Mining, Textual Entity Recognition, Collaborative Filtering exercises that teach how to manipulate data sets using parallel processing with Spark.

  • Introduction to big data
  • Hadoop
  • Map Reduce
  • Hive
  • Introduction to Spark
  • Big Data Bottlenecks
  • Spark architecture
  • Spark in Scala
  • Using SparkSQL and Dataframes
  • SparkSQL actions with Scala programs
  • Spark Streaming
  • Spark Machine Learning Techniques
  • Lab
  • Project
Big Data & Cloud Architecture

Enterprise IT has came a long way from the era of monolithic software and bundled hardware and has evolved into the modern micro-services and exible deployment paradigms. Past few years have seen rapid developments in many technologies such as containerization and software de ned networks. Cloud o erings have gone way beyond simple storage and compute services. Big Data is yet another world in its own right and there are dozens of components to choose from.

The areas of Big Data, IoT and Cloud are converging and it can be daunting to gure out the optimal architecture to achieve an objective.

This introductory course touches several topic including di erent deployment models on cloud, mixing public and private clouds, container orchestration platforms and service architectures. This course will also cover di erent components in the Hadoop ecosystem and discuss architectural choices.

  • Infrastructure as a Service
  • Platform as a Service
  • Software as a Service
  • Container Orchestration
  • Clustering Platforms
  • Private Cloud Platforms
  • Serverless Computing
  • Scaling & Load Management
  • Databases and Data Formats
  • Data Pipelines & Message Queuing
  • Mediation & ETL Tools
  • Analytics Execution Engines
  • Data-warehousing & Visualization
  • Machine Learning & AI Platforms
  • Application Optimization & Delivery
  • Continuous Integration

Our courses are taught academically as standard 45 hours courses. All the courses include a well crafted plan to ensure learning through assignments, quizzes and hands-on exercises.

The courses can be customized for each customer considering the training recipients and objectives.

Download Learning Handbook

Watch this space for our upcoming publicly available courses and registration details.

We have delivered solutions and learning to customers in telecom, law enforcement and academia.

Telenor Ministry of Defence UK Pakistan Army Aegis School of Business, Data Science and Telecommunication University of Management & Technology

The Team

The core strenght of Percipience Analytics are the people. Our team members never back off from a challenge and always take an intellectual and thorough approach towards solving them.

Muzaffar Haider Ali, PhD
Chief Executive Officer

Muzaffar has held senior leadership positions at multinational engineering conglomerates and has steered several mega projects to completion.

Abbas Raza Ali
Chief Data Scientist

Abbas has succesfully delivered solutions to several industries in four continents and has several publications in machine learning, big data & NLP.

Jaffar Hussain
Chief Architect

Jaffar has diverse experience in several technology domains including telecommunications, cloud, big data, solution and enterprise architecture.

Our subject matter experts belong to several industries and scientific areas. Most of them are full time researchers, others are involved in commercial ventures.

Damien Fay, PhD
Big Data Analytics
Hasan Jamal, PhD
Parallel Computing
Hassan Mohy-ud-Din, PhD
Medical Imaging
Maissom Abbasi, PhD
User Experience
Martin Sewell, PhD
Finance, Environment
Mehreen Saeed, PhD
Machine Learning
Nakhat Fatima, PhD
Natural Language Processing
Ricardo Prudêncio, PhD
Meta Learning, Social Graphs

We have spent a lot of time learning and building up skillsets and tools to put a dent in the universe. And yes, our favourite story is that of David and Goliath.

Started in 2010 as R&D company, started offering business solutions in 2016. Completed commercial projects in 2017.
Started in 2010 as R&D company, started offering business solutions in 2016. Completed commercial projects in 2017.

Let's Talk

I agree to be contacted and recieve newsletter.

16-A, Hali Road, Gulberg II, Lahore, Pakistan

+92 42 35876431

120 High Road, East Finchley, London N2 9ED, UK

+44 70 42073548

Victorious warriors win first and then go to war, while defeated warriors go to war first and then seek to win.