Conceptual Frameworks for Information Science Tasks

Word: All figures within the following sections have been created by the creator of this text.

Widespread Framework Varieties

Though conceptual frameworks are available many various styles and sizes, 4 primary framework sorts stand out as being particularly widespread in information science tasks: hierarchies, matrices, course of flows, and relational maps. We’ll briefly go over every of those framework sorts under.

Hierarchies

Hierarchical frameworks typically take the type of tree diagrams, beginning with a root node and ending with a number of leaf nodes, as proven in Determine 1. For instance, the foundation node might symbolize an overarching idea in a taxonomy or an preliminary binary query in a call tree. A node’s place within the hierarchy (or tree) provides us precious details about its relationship to different nodes. Though Determine 1 labels the objects within the hierarchy as “ideas,” they are often any type of entity. Entities could also be impartial (e.g., ideas, matters, segments) or have some constructive or damaging valence (e.g., revenues, prices, issues, points). The hierarchical construction can range in depth and breadth.

In visible representations of hierarchies, vertical hyperlinks between two entities are usually drawn explicitly and may be non-directional (easy strains) or directional (downward or upward arrows, relying on the movement of the connection). Against this, horizontal hyperlinks between entities on the identical degree of a hierarchy are usually not proven explicitly. Identical-level entities could also be topic to a pure ordering (e.g., temporal or spatial), which may be proven by putting them accordingly within the framework. As an example, entities that happen earlier in an ordering must be positioned to the left of entities that happen later. If the entities don’t include a pure ordering, you possibly can nonetheless contemplate ordering them ultimately (e.g., by degree of significance or precedence) to assist reasoning. Entities on the identical degree in a hierarchy ought to typically even be on the identical degree of abstraction.

In lots of conditions, it helps if the nodes of a hierarchy are mutually unique and cumulatively exhaustive, or MECE (pronounced “me-see”), to a big extent. Being mutually unique implies that the ideas represented by particular person nodes haven’t any main overlaps (i.e., no redundancies), whereas being cumulatively exhaustive implies that the framework leaves out nothing essential. A MECE hierarchy may be helpful for breaking down a broad idea into sub-concepts (or elements) to establish key drivers of the entire.

Matrices

A matrix is a tabular information construction consisting of n rows and m columns. Information scientists engaged on tabular use instances routinely leverage matrices for storing coaching information and mannequin weights. Coaching machine studying fashions can yield high-dimensional matrices of weights that seize complicated relationships between predictors and targets. Low-dimensional matrices just like the one proven in Determine 2 may be helpful for analyzing issues and speaking key insights.

The generic two-by-two matrix proven in Determine 2 compares two completely different dimensions in opposition to one another. Such a matrix naturally yields 4 quadrants. By conference, the bottom-left quadrant (the place each dimensions are “low”) is often the undesirable area of the matrix, and the top-right quadrant (the place each dimensions are “excessive”) represents the fascinating area. For instance, the market analysis agency Gartner makes use of two-by-two matrices to investigate the aggressive panorama in numerous business sectors and calls the top-right area of the matrix (the place the market leaders are plotted) the “magic quadrant.”

The size of a matrix might symbolize steady, ordinal or categorical information sorts. Ideally, these dimensions (or axes) must be essential to the overarching framework goal ultimately (e.g., key sub-concepts, issues, or drivers in a given context). The interactions between these dimensions must be of explicit curiosity as a supply of perception, since it’s these interactions that matrices can seize effectively.

Generally, the MECE precept additionally applies to the selection of dimensions — they need to collectively cowl the essential sub-concepts or drivers of the issue being investigated and keep away from redundancies. In any other case, trying on the interplay will likely be no completely different from a person dimension. If analyzing the interplay is just not essential, a hierarchical framework could also be extra appropriate. Changing between a matrix framework and its hierarchical analog may be simple. As an example, to remodel the matrix in Determine 2 right into a hierarchy, create a root node that defines the general context, let its little one nodes be Dimensions 1 and a pair of, and let their respective little one nodes be “excessive” and “low.”

Course of Flows

A course of movement defines a sequence of logically ordered actions that work together to attain an overarching goal. As an example, instruments reminiscent of Dataiku and KNIME permit customers to assemble information science pipelines as course of flows, going from information ingestion all the best way to modeling and report era. Determine 3 depicts a generic course of framework.

The entities of the method in Determine 3 are labeled as actions, however these may very well be steps, phases, operations, and many others. The method begins with an exercise (Exercise 1), ends with an exercise (Exercise 3), and has a number of actions in between (Exercise 2). Some inputs are usually fed into the method at first and remodeled over the sequence of actions to yield an output. Word that inputs and outputs also can enter and depart at intermediate steps throughout the course of.

As with hierarchies and matrices, the MECE precept may be essential in formulating the completely different actions of the method. If two actions have important conceptual overlap, you could possibly contemplate both grouping them right into a single exercise or breaking them up right into a extra granular set of distinct actions. As an example, the intermediate actions in Determine 9 might have resulted from this form of evaluation; Exercise 2 may very well be the result of merging some overlapping actions, whereas Actions 2.1-2.3 may very well be a granular breakdown of a particular subset of these merged actions. If an exercise or a bigger a part of the method repeats, then it may be represented as a cycle, whereby an exercise transitions to a different exercise that has already occurred earlier than.

The transition from one exercise to a different ought to meaningfully rework the inputs of the method (e.g., by rising, decreasing, combining or in any other case altering the inputs ultimately) with the purpose of manufacturing the specified output. If a transition doesn’t change the inputs, then the 2 actions on both aspect of the transition are seemingly redundant and must be merged or break up up in another way, as mentioned above.

Relational Maps

Relational maps shift the main focus from particular person ideas (or entities) to the relationships between them. Information scientists working with data graphs or box-and-arrow “path diagrams” of causal relationships (as proven in Determine 4) will likely be conversant in this framework kind.

A relationship can typically be any operate that hyperlinks two completely different ideas collectively. 4 kinds of relationships are particularly widespread:

• Transactional: A relationship can symbolize a number of transactions between entities. The transactions might contain the movement of tangible issues (e.g., merchandise purchased and bought) or intangible issues (e.g., data, cash). Transactional relationships can incorporate directionality; a transaction can movement from A to B, from B to A, or in each instructions, and every of those instances has a special that means for the entities (e.g., they could be receivers, senders, or each).
• Causal: Entities A and B could also be causally associated if A is accountable — no less than partly — for the prevalence or state of B (or vice versa). The character of the causal relationship might range. The position of A is powerful if its presence is enough to completely trigger B (though A will not be the one entity that may totally trigger B). The position of A can also be robust whether it is essential to trigger B (though A might not be capable to do that alone). Furthermore, if A causes B, it doesn’t essentially observe that B causes A; the notion of directionality is clearly essential for specifying causal relationships.
• Similarity-based: Entities could also be associated as a result of they’re comparable or dissimilar ultimately. For instance, entities A and B may be comparable as a result of they have a tendency to seem in the identical place or occur on the identical time (and dissimilar if the prevalence of 1 entity tends to preclude the prevalence of the opposite). The notion of correlation is a mathematical formalization typically used to assemble measurable, similarity-based relationships. Word that, simply because two entities are correlated doesn’t essentially imply that they’re causally associated (though if they’re causally associated, then they’d even be correlated).
• Membership-based: Entities may be linked collectively by being members of the identical group, neighborhood, or class. As an example, individuals may be associated by being in the identical neighborhood, grocery objects may be a part of the identical product class, and a set of sub-concepts could also be a part of an overarching idea. Certainly, one may apply a hierarchical framework to drill down into successively deeper ranges of membership inside entities into account.

How you can Construct Your Personal Frameworks

The next three-step course of can be utilized to construct a customized framework:

1. Outline the framework’s goal.
2. Establish the correct constructing blocks (i.e., the framework kind and dimensions).
3. Put the constructing blocks collectively in an efficient method to reply the framework’s goal.

Step 1: Outline the Goal

In defining the framework’s goal, ask your self: In what context will the framework be used? What ought to the framework accomplish? Can an current framework be reused — maybe with some minor modifications — or does a brand new one must be constructed to suit your particular wants?

The development of the framework must be tied to a better purpose, such because the supply of a undertaking, formulation of a call, or creation of some documentation. As soon as the context has been correctly understood, cautious consideration must be given to what the framework ought to accomplish in concrete phrases. Is the framework meant as a decision-making software? Is the framework meant to construction the movement of an argument in a report or a presentation?

Simply since you want a framework doesn’t imply that you have to construct one your self. In lots of conditions, current conceptual frameworks may be reused with out important modification. Spending some effort to take care of a stable, up-to-date overview of related current frameworks avoids downstream prices of “reinventing the wheel.” Reusing current frameworks has advantages past not having to begin from scratch; if the framework has been round for a while, its primary options, in addition to its strengths and limitations, could also be well-documented and examined in several settings. Platforms reminiscent of In direction of Information Science are an important supply for maintaining abreast of conceptual frameworks associated to information science tasks.

Step 2: Establish the Framework Kind and Dimensions

Having clarified the target of the framework, it’s time to suppose extra concretely concerning the building of the framework itself. One of many primary difficulties right here is that conceptual frameworks are inherently not as tangible as bodily ones (like molds in a manufacturing facility). We are inclined to intuit the hyperlink between type and performance — the framework and its goal — extra simply when the framework and its object are tangible. The hallmark of an excellent conceptual framework is its capacity to show a seemingly intangible argument or choice into one thing extra tangible, and the important thing to that is illustration.

Broadly talking, there are two facets that decide the illustration of conceptual frameworks: the kind of the framework and the dimensions of the framework. You’re prone to discover the framework kind first because it determines how the framework seems as an entire. The earlier sections lined the 4 widespread framework sorts. The framework dimensions dictate what the framework can particularly symbolize (e.g., when it comes to granularity and ordering). By adjusting the size, the identical framework kind may be reused to generate a variety of various insights. Following are three widespread lessons of framework dimensions:

• Categorical: These dimensions include a finite set of discrete classes that totally describe the dimension. The classes needn’t be ordered (e.g., a set of merchandise, buyer segments, gender).
• Ordinal: These dimensions are ordered, which suggests which you could analyze whether or not one thing is “lower than,” “higher than,” “equal to,” and so forth, in relation to one thing else (e.g., damaging/constructive, low/medium/excessive).
• Steady: Such dimensions can take the notion of ordinal dimensions to a way more granular degree. Being steady implies that the dimension is numerical and may embrace decimals (e.g., 1.23, -2.718, 3.14159).

Step 3: Put It All Collectively

As soon as the framework kind and dimensions have been recognized, they are often mixed to provide a customized framework. Typically, the identification and mixture steps aren’t explicitly separated, because you not often do one with out the opposite. However the framework kind and its dimensions — the fundamental constructing blocks — aren’t essentially wedded to one another. Some mixtures might make extra sense than others, and you may typically combine and match the constructing blocks in some ways, over a number of iterations, till the framework feels proper. Have the ability to spot and exploit this combinatorial flexibility is a vital talent that it is best to begin growing from the outset of your framework-building journey.

Furthermore, there are broadly 4 “pathways of study” that seize the hyperlink between the framework and its goal:

• Descriptive: Approaches the framework’s goal by gathering and organizing previous data (e.g., utilizing visuals reminiscent of graphs and tables, or written summaries). Doing so permits us to raised describe and analyze what occurred up to now, however it could not essentially inform us why one thing occurred, or whether or not it’ll occur once more.
• Diagnostic: Takes descriptive data of previous occasions and goes a step additional to have a look at why one thing occurred. That is completed by drilling down into the info, mining for clues and correlations, and looking for a believable hyperlink between trigger and impact. As with the descriptive pathway, the main focus is on the previous.
• Predictive: Differs from the prior two by asking and answering questions concerning the future. The main focus is on making an informed guess about what’s going to occur sooner or later by counting on a bunch of usually quantitative methods that vary from the straightforward (e.g., primary chance principle, linear fashions) to the extra complicated (e.g., neural nets).
• Prescriptive: Goes past merely predicting future occasions to recommending methods to cope with them. The main focus is on determining the right way to make one thing occur — or whether or not it ought to occur — sooner or later. The reasoning for the prescription may be quantitative (e.g., based mostly on statistics or simulation modeling) or qualitative (e.g., based mostly on private expertise).

Framework sorts and dimensions can due to this fact be mixed in several methods to provide customized frameworks that lend themselves to descriptive, diagnostic, predictive, and prescriptive use instances.

Prime Ideas

This part provides 5 ideas for constructing good conceptual frameworks. The ideas are certainly not an exhaustive listing of the factors that it is best to contemplate, however symbolize a primary set of issues to remember.

Tip 1: Deal with the Goal and Viewers

The method of constructing frameworks broadly consists of three steps, particularly defining the target, then figuring out and mixing the constructing blocks (framework sorts and dimensions) accordingly. Whereas step one will, by its nature, emphasize the strategic goal and audience of the framework, the main focus within the latter two steps shifts to the nitty-gritty particulars of the framework’s constructing blocks. The deeper you get into the mechanics of the framework, the more durable it may be to take care of visibility of the unique goal. To take care of visibility of the larger image, it could possibly assist to take a step again sometimes through the framework-building course of and remind your self of the strategic goal and audience. It could additionally assist to delay a part of the evaluation till the required information turns into accessible and to hunt common suggestions from colleagues and the audience of your framework the place attainable.

Tip 2: Preserve It as Easy as Attainable

To paraphrase a quote typically attributed to Albert Einstein — one of the crucial achieved builders of conceptual frameworks of the final century — we will say {that a} framework must be made so simple as attainable, however not less complicated. Because the course of inherently entails making an attempt out completely different mixtures of framework sorts and dimensions, it could possibly typically be tempting to snap increasingly items collectively. But sacrificing simplicity can probably diminish the broader worth of the framework in apply. Complicated frameworks may be obscure, apply, consider, and construct — chances are you’ll must confirm a number of assumptions and preconditions, and modify many various levers throughout the framework.

Tip 3: Make It MECE 

Making certain {that a} framework is MECE has some essential benefits. From a theoretical standpoint, being MECE implies that the sub-concepts observe a constant, additive part-whole logic; you anticipate the sub-concepts to “add up” to type the larger idea. Crucially, this logic permits you to substitute the set of sub-concepts for the larger idea (and vice versa) all through your evaluation. The additive logic of MECE additionally enables you to evaluate completely different ideas in a rigorous method; as an alternative of claiming that two ideas are comparable, you possibly can state exactly the extent to which they’re comparable by figuring out the sub-concepts they share. From a sensible perspective, being MECE means which you could “divide and conquer” huge issues effectively and options to some sub-problems could also be reusable. Typically you possibly can even attain the answer of the larger downside with out fixing all of the sub-problems (e.g., if the larger downside may be represented as a disjunction of the sub-problems). Bypassing sub-problems additionally works if you find yourself fixing the larger downside inductively (e.g., as in mathematical induction).

Tip 4: Make It Versatile 

Essentially, a conceptual framework must be designed to fulfill its total goal, so chances are you’ll be questioning why flexibility is a vital facet to think about. In apply, there are no less than two kinds of conditions during which flexibility generally is a huge assist. Within the first state of affairs, chances are you’ll be coping with an goal that may be a shifting goal, with some components of the target’s full scope altering (even barely) sometimes; responding to such scope modifications generally is a ache if some flexibility is just not baked into the framework. Within the second state of affairs, your framework might should bear a number of iterations, during which completely different framework sorts and dimensions are added, modified and eliminated over the course of the framework’s evolution; a versatile design makes it a lot simpler to facilitate such alterations of the framework’s form and content material. Modularity, scalability, robustness, extensibility, and portability — whereas usually related to software program engineering and structure — are additionally related design issues for constructing versatile conceptual frameworks.

Tip 5: Construct It Iteratively 

It could be nice for those who may provide you with the right framework in a single go, nevertheless it not often works out that manner. A number of elements could make the primary iteration extra of a primary draft, to be adopted by no less than a couple of extra. The overarching goal — and particularly the operational implications with regards to constructing the framework — will not be totally clear at first. Over a few iterations, nevertheless, you’ll in all probability start to get the cling of which framework sorts and dimensions work and which don’t. Whereas your output after a given iteration could also be removed from excellent, it may nonetheless quantity to a minimal viable product (MVP) if it yields a viable answer to the overarching goal with minimal effort and complexity. The MVP may be examined (e.g., with precise information and actual customers) to grasp its strengths and weaknesses. Every successive iteration can produce an improved MVP by including, eradicating or altering options of the earlier iteration.

To shut off, here’s a video that shares some extra good recommendation on constructing and utilizing conceptual frameworks:

The Wrap

Conceptual frameworks assist us flip summary concepts into concrete, tangible merchandise that different individuals can see, use, and admire. This may be particularly essential for information scientists, or so-called “data employees,” whose jobs contain amassing, analyzing, and deriving conclusions from information. If you’re studying this text, you might be in all probability a data employee. To paraphrase well-known administration guru Peter Drucker, “It’s information that allows data employees to do their job,” however it’s the capacity to meaningfully manage this information that results in a job effectively completed — and that, in a nutshell, is why the correct use of conceptual frameworks can assist the profitable design and supply of information science tasks.