Support Vector Machines (SVM)

 

Snooker SVM

Support vector machines (SVMs) are powerful tools for data classification. Support vector machines (SVMs) are used for classification of both linear and nonlinear data. Classification is achieved by a linear or nonlinear mapping to transform the original training data into a higher dimension. Within this new dimension, it searches for the linear optimal separating hyperplane (i.e. a “decision boundary” separating the tuples of one class from another). With an appropriate nonlinear mapping to a sufficiently high dimension, data from two classes can always be separated by a hyperplane. The SVM finds this hyperplane using support vectors (“essential” training tuples) and margins (defined by the support vectors).SVM’s  became famous when, using images as input, it gave accuracy comparable to neural-network with hand-designed features in a handwriting recognition task.

Support vector machines select a small number of critical boundary instances called
support vectors from each class and build a linear discriminant function that separates
them as widely as possible. This instance-based approach transcends the limitations
of linear boundaries by making it practical to include extra nonlinear terms in
the function, making it possible to form quadratic, cubic, and higher-order decision
boundaries.

SVM’s are based on an algorithm that finds a special kind of linear model: the maximum-margin hyperplane. The maximum-margin hyperplane is the one that gives the greatest separation between the classes—it comes no closer to either than it has to.

Using a mathematical transformation, it moves the original data set into a new mathematical space in which the decision boundary is easy to describe. Because this transformation depends only on a simple computation involving “kernels,” this technique is called the kernel trick. kernel can be set to one of four values: linear, polynomial, radial and sigmoid.

SVMs were developed by Cortes & Vapnik (1995) for binary classification.

Class separation: We are looking for the optimal separating hyperplane between the two classes by maximizing the margin between the classes’ closest points |the points lying on the boundaries are called support vectors, and the middle of the margin is our optimal separating hyperplane.

Overlapping classes: Data points on the “wrong” side of the discriminant margin are weighted down to reduce their influence ( “soft margin” ).

Nonlinearity: when we cannot find a linear separator, data points are projected into an (usually) higher-dimensional space where the data points effectively become linearly separable (this projection is realised via kernel techniques ).
Problem solution: the whole task can be formulated as a quadratic optimization problem which can be solved by known techniques.

A program able to perform all these tasks is called a Support Vector Machine.

Graphing my Facebook network – Social Network Analysis

Pradeep Facebook Network

Netvizz is a cool tool which can export your Facebook data in a format which makes it easier to visualize or do a network analysis offline. There are other apps available on the Facebook platform which perform this using predefined bounds within the app itself but what I like about Netvizz is that it allows you to extract this information and play with it using any tool you are comfortable with like R, Gephi etc. This sort of visualization is a core of Social network analysis systems.
I spent some time to play around with my Facebook network information over the weekend. I extracted out my network using Netvizz. It gives a GDF file with all the necessary information and can be imported into Gephi directly. The idea was to see how much the Facebook visualization of my friend network compares with my real life network. I do understand that the online world and the offline world social networks differ but on a massive system like Facebook my guess was that it should mirror my real life network much more realistically. I built the network and used the community detection algorithm and did a ForceAtlas2 layout. This is the network visualization I ended up with after tweaking a few things. The network diagram is both surprising and a bit scary.

Accurate reflection of my Social network groups: The network analysis shows the various groups of friends by my life events and their relationships. The green bunch of circles on the right are my friends from my ex company Logica. The small red bunch below is my network of friends from IIM-Lucknow and the big blob of circles on the top left are my friends from Dell. There were other individual circles in-between too which were removed because I filtered by degree of connectedness and represented friends who were not part of any of these big networks and were people with whom I was connected outside of all these bigger networks
The network information on Facebook is more or less an accurate reflection of my networks in real life in terms of how I could group them by connectedness or with specific timelines of my life.

Not so Accurate reflection of my Social network groups: My assumptions of who were the best networkers was shattered when I could see that the some of the people in the top 10 in degree of connectedness were actually people who are more of introverts. Maybe the online world provides them a degree of comfort in connecting with people. Another surprise was that some of my friends in these disparate networks were also connected with each other. This can be seen by the 2 dots at the bottom connecting the bigger blob to them. Another aspect was that this is still not an accurate reflection of my actual social life and does not in any way reflect my actual day to day social interactions.

Inference on Connectedness: The connected inference was also surprising since it was an accurate reflection on the groups of people and their interactions. I was pretty surprised on how even within my current organization the connectedness numbers could pinpoint teams. This is reflected in the big blob on the top right which has 3 distinct colors representing the 3 large divisions I have worked across in my organization.

I will be playing around a lot more with this data and I am planning a further analysis on my LinkedIn network and overlay it onto my Facebook network to see how it compares.

Strategy Execution

Strategy helps an organization position itself uniquely in order to create value and exploit the unfolding opportunities , hedge against threats, leverage strengths and remove weaknesses.

Strategy execution has two components namely the action planning to operationalize the core strategy and its physical implementation. Strategy execution is one integrated in which action planning and physical implementation are integrated in real time basis.  High quality execution presupposes high quality action planning , assigning the right people for the right jobs, adequate follow through and robust MIS and review processes. Strategy execution involves the optimal balancing of seven key variables namely Strategy, Structure, Systems , Staff, Skills, Style and Shared values. Strategy execution is the key role of the business leader. This execution is a discipline and must be learned specifically. The primary areas are

  • Project Management
  • Scheduling
  • Cost Management
  • People Management
  • Time Management
  • Interpersonal skills
  • Negotiation and Conflict resolution
  • Problem solving skills
  • Communication skills
  • Relationship management
  • Risk management
  • Balance Scorecard

The four building blocks of Strategy execution are

  • Information flow
  • Decision Rights
  • Right motivators
  • Right Structure

 

Information flow plays a key role in ensuring that information about competitive environment is received at the appropriate time at all appropriate levels and that information flows freely across organization boundaries. It is also critical to ensure that field and line employees have the information they need to understand bottom line impact of their day to day choices, Line managers have access to metrics they need to measure key drives of their business and that conflicting messages are rarely sent.

Decision rights ensures that everyone has a good idea of the decisions and the actions for which they are responsible and senior managers have a good feel about the operating decisions being made. The decision making culture in an organization is one of persuasion and consensus rather than command and control

 

Motivators

 

Structure

Concept of Strategy and Strategy Process

In the new business environment customers are not just demanding but they also have infinite options. Competition is not just intensifying but there are new sources of competition. Resources too are not just limited but they are fluid and move fast. Investors are impatient and look at above average returns consistently and constantly. Huge opportunities coexist with massive risks. An organization must think and act differently and smartly in order to face the new environmental context.  Strategy derived through the strategy process is what makes the organization stand apart from ”also rans” and perform differently.

Strategic decisions are Context specific and indicate long term direction of an organization. These decisions define the context specific sustainable competitive advantage of the organization. It establishes the scope of the organization and the strategic fit between resources , activities and environmental contingencies. Strategic decisions aim to  exploit existing capabilities or explore new opportunities and requires major resource commitments and is irreversible in the short run. It affects all organizational decisions and is shaped by values and expectations of key stake holders with the primary aim of wealth creation. It specifically helps answer three questions for each business in the portfolio namely

  1. Where to Compete? ( Market selection )
  2. How to win orders? ( Build Competitive advantage)
  3. How to deliver? ( Value delivery process )

Strategic decisions are complex in nature and require a vision for the future. It demands an integrated approach to managing an organization. It requires a change within the organization and management of relationships and networks outside the organization.

There are different types of strategy namely

  1. Corporate / Portfolio Strategy : Portfolio strategy also called corporate strategy involves portfolio selection  considering synergy and risk return criterion. It decides resource allocation ( Organizational, Financial, people etc. ) across businesses.
  2. Business Strategy : Business strategy is a set of decisions that helps a business position itself uniquely and distinctly.
  3. Functional Strategy : Functional strategies includes strategies and programs at functional level to operationalize the overall strategy and align them to each other.
  4. Operational Strategy : Operational strategy includes action plans and programs at the frontlines of an organization where strategy gets operational.

External Environment, Opportunities, Threats, Industry competition and Competitor analysis.

External environment: General, Industry and Competitor.

The external environment includes the areas of General, Industry and Competitor environment. The general environment is the broader society dimensions that influence an industry and the firms within it. It is grouped into 7 dimensions or ‘environmental segments’ which cannot be controlled or manipulated. However segment intelligence of each of these can help reorient strategy to mitigate influence in the long term.

clip_image001[1]

The industry environment is a set of factors which directly influence a firm’s competitive actions and responses. These factors can be analysed using Porters Five forces model. Competitor Analysis is used to gather and interpret competitor information. The Competitor environment gives information about a firms direct and indirect competitors and the competitive dynamics expected to impact a firms efforts to generate an above average return.

External Environment Analysis.

An Opportunity is a general environment condition that is exploited helps a company achieve strategic competitiveness. A threat is a general environmental condition that may hinder a company’s efforts to achieve strategic competitiveness. There are four components of external environmental analysis namely

  • Scanning: is the process of identifying early signal of environment changes and trends.
  • Monitoring: is the process of detecting meaning through ongoing observation of environmental changes and trends obtained through scanning.
  • Forecasting: is the process of developing projections of anticipated outcomes based on monitored changes and trends.
  • Assessing: is the process of determining the timing and importance of environmental changes and trends that impact a firms strategies and their management.

clip_image003[1]

 

Industry environmental analysis

An industry is defined as a group of firms producing products that are close substitutes the industry environment has a higher impact on a firm’s general competitiveness and ability to earn above average return compared to the general environment. The intensity of competition and profit potential are a function of Porters Five forces analysis.

clip_image005[1]

Porters Five Forces

  1. Threat of new Entrants: New entrants can threaten market share of existing competitors. It brings additional production capacity to the industry. This is a function of two factors namely
      1. Barriers to Entry : Economies of scale, Product differentiation, Capital requirements, Switching costs, Access to distribution channels, Cost disadvantage, Government policy are the various barriers to entry faced by a new entrant into an industry.
      2. Expected Retaliation: An expectation of vigorous and swift retaliation reduces the likelihood of entry. Retaliation is generally vigorous when the existing firm has a large stake in the industry, invested substantial resources and when industry growth is slow.
  2. Bargaining Power of Suppliers: Suppliers can exercise their power by reducing quality or increasing price. Suppliers are powerful when there are very few large suppliers and are they are more concentrated than the industry they sell to, there are no substitutes for the supplier’s product, the firms are not a significant customer to the supplier group, the supplier’s goods are critical to a buyer’s success, there is a high switching cost due to effectiveness of a suppliers products. and ther exists a threat of forward integration.
  3. Bargaining power of buyers: Buyers want to buy at the lowest price and demand higher levels of service at the best quality. They are powerful when they purchase a large proportion of the industries output. The products sales accounts for a significant portion of the seller’s annual revenue. The industries products are undifferentiated and standardized raising the threat of backward integration.
  4. Threat of substitute products: is the threat when goods or services outside of the given industry perform the same or similar functions at a competitive price or have low switching costs. Product and service differentiation helps overcome the threat of substitute products. E.g. Plastic has replaced steel and other materials in many applications at a very competitive price and value preposition.
  5. Intensity of rivalry among competing firms: The intensity of rivalry in an industry is the extent to which competitors within an industry compete with one another and limit other profit potential. If rivalry is fierce the profit potential in the industry declines for all firms. Low intensity of rivalry increases profit potential and makes the industry less competitive. Intensity of Rivalry is high if
        • Competitors are numerous
        • Competitors have equal size
        • Competitors have equal market share
        • Industry growth is slow
        • Fixed costs are high
        • Products are undifferentiated
        • Brand loyalty is insignificant
        • Consumer switching costs are low
        • Competitors are strategically diverse
        • There is excess production capacity
        • Exit barriers are high

Intensity of Rivalry is Low if

        • Competitors are few
        • Competitors have unequal size
        • Competitors have unequal market share
        • Industry growth is fast
        • Fixed costs are low
        • Products are differentiated
        • Brand loyalty is significant
        • Consumer switching costs are high
        • Competitors are not strategically diverse
        • There is no excess production capacity
        • Exit barriers are low

Competitor Analysis

Competitor intelligence is the data and information that a firm gathers to better understand and anticipate its competitor’s objectives, strategies, assumptions and capabilities.When gathering competitive intelligence firms must pay specific attention to complementors who add value to the focal firms products and strategies. E.g. Microsoft and Intel are complementors.Competitor Intelligence collection needs to follow ethical practices which can be through obtaining and analysing public information or attending trade fairs, obtaining brochures etc.

WS-Trust — 7

WS-Trust — 7

A SOAP message using WS-Security is protected by security tokens. These security tokens can be obtained in a variety of ways such as username/password or x509 certificate, Kerberos e.t.c. Even though the SOAP message is now protected the recipient may not be able to use the token due to

1. Security token format incompatibility: The recipient may find the token format incompatible.

2. Security token trust: Even if the recipient can understand and process the token the recipient may be unable to map the trust hierarchy of the token to its own.

3. Namespace: The recipient may be unable to understand the claims within the token.

WS-trust aims to address these issues by defining a request/response protocol and by introducing a security token service. WS-Trust defines standard mechanisms for

Security token creation, management, exchange and also for establishing trust relationships. WS-Trust thus builds upon WS-Security.

The Security Token Service (STS) is responsible for Token Issuance, Validation, Renewal & exchange. The requests are sent as RequestSecurityToken (RST) message specifying the operation type (Issue, Validate e.t.c) and the token type can also be specified optionally. WS-Trust defines further extensions to the RST message specifying delegation, forwarding and proxy requirements for the tokens. In addition lifetime and renewal requirements can also be specified.

The request structure is as follows


--Request Header
... --Defines the security token type(X509…)
... --Defines the request type( Issue , cancel ..)
... --Reference tokens
... --supporting tokens

A sample RequestSecurityToken(RST) message is as follows

http://docs.oasis-open.org/wss/oasis-wss-saml-token-profile-1.1#SAMLV1.1

http://schemas.xmlsoap.org/ws/2005/02/trust/Issue

The response is returned as RequestSecurityTokenResponse(RSTR) containing the security token. The response structure is as follows

àResponse Header.

... àThe token type returned.

... àThe Key used in the token.

... àThe key size.

... àThe scope to which the token applies

... àThe security token

... àProof of possession token

A sample RSTR message is given below

http://docs.oasis-open.org/wss/oasis-wss-saml-token-profile-1.1#SAMLV1.1

...

...