Financial

Technology
Unit 2
By: Ms. Sapna Kataria
 What is the Internet of Things?
The IoT may sound like a sci-fi series where everyday objects come to life, but it's more subtle than that.
Think:
•Smart switches that talk to smartphones
•Smart TVs playing videos from a laptop
•Smart thermostats that sync with your smartwatch
The Internet of things (IoT) describes devices with sensors, processing ability, software and other technologies
that connect and exchange data with other devices and systems over the Internet or other communications networks.
The Internet of things encompasses electronics, communication, and computer science engineering. "Internet of
things" has been considered a misnomer because devices do not need to be connected to the public internet; they
only need to be connected to a network and be individually addressable.[7][8]
The field has evolved due to the convergence of multiple technologies, including ubiquitous
computing, commodity sensors, and increasingly powerful embedded systems, as well as machine learning.[9] Older
fields of embedded systems, wireless sensor networks, control systems, automation (including home and building
automation), independently and collectively enable the Internet of things.In the consumer market, IoT technology is
most synonymous with "smart home" products, including devices and appliances (lighting fixtures, thermostats,
home security systems, cameras, and other home appliances) that support one or more common ecosystemsiand can
be controlled via devices associated with that ecosystem, such as smartphones and smart speakers. IoT is also used
in healthcare systems.[11]
 The Internet of Things (IoT) has a wide range of applications across various domains. Let’s explore some of them:
1.Wearables:
1. Wearable technology, a hallmark of IoT applications, includes devices like fitness trackers, heart rate monitors,
and smartwatches.
2. For instance, the Guardian glucose monitoring device helps people with diabetes by detecting glucose levels in
the body using a small electrode called the glucose sensor under the skin. It then relays this information to a
radiofrequency monitoring device1.
2.Smart Home Applications:
1. The smart home is one of the most common IoT applications.
2. Examples include AI home automation, where systems control in-house functions based on musical notes,
and Mark Zuckerberg’s home automation system1.
3.Healthcare:
1. IoT applications can transform reactive medical-based systems into active wellness-based systems.
2. By improving device power, precision, and availability, IoT enhances medical research and patient care 1.
4.Smart Cities:
1. Smart cities leverage technology to provide services and enhance urban living.
2. These services include improving transportation, social services, promoting stability, and giving voice to citizens
Machine learning (ML) is a field of study in artificial intelligence concerned with the
development and study of statistical algorithms that can learn from data and generalize to
unseen data, and thus perform tasks without explicit instructions.[1] Recently,
generative artificial neural networks have been able to surpass many previous approaches in
performance.[2][3]
Machine learning approaches have been applied to many fields including large language
models, computer vision, speech recognition, email filtering, agriculture, and medicine,
where it is too costly to develop algorithms[4] to perform the needed tasks.[5][6] ML is known
in its application across business problems under the name predictive analytics. Although
not all machine learning is statistically based, computational statistics is an important source
of the field's methods.
The mathematical[7] foundations of ML are provided by mathematical
optimization (mathematical programming) methods. Data mining is a related (parallel) field
of study, focusing on exploratory data analysis through unsupervised learning.[9][10] From a
theoretical point of view Probably approximately correct learning provides a framework for
describing machine learning.
Artificial intelligence[edit]
Machine learning as subfield of AI[27]
As a scientific endeavor, machine learning grew out of the quest for artificial intelligence (AI). In the early days of AI as an academic discipline,
some researchers were interested in having machines learn from data. They attempted to approach the problem with various symbolic methods, as
well as what were then termed "neural networks"; these were mostly perceptrons and other models that were later found to be reinventions of
the generalized linear models of statistics.[28] Probabilistic reasoning was also employed, especially in automated medical diagnosis.[29]: 488
However, an increasing emphasis on the logical, knowledge-based approach caused a rift between AI and machine learning. Probabilistic
systems[30] were plagued by theoretical and practical problems of data acquisition and representation.[29]: 488 By 1980, expert systems had come to
dominate AI, and statistics was out of favor.[31] Work on symbolic/knowledge-based learning did continue within AI, leading to inductive logic
programming, but the more statistical line of research was now outside the field of AI proper, in pattern recognition and information
retrieval.[29]: 708–710, 755 Neural networks research had been abandoned by AI and computer science around the same time. This line, too, was
continued outside the AI/CS field, as "connectionism", by researchers from other disciplines including Hopfield, Rumelhart, and Hinton. Their
main success came in the mid-1980s with the reinvention of backpropagation.[29]: 25
Machine learning (ML), reorganized and recognized as its own field, started to flourish in the 1990s. The field changed its goal from achieving
artificial intelligence to tackling solvable problems of a practical nature. It shifted focus away from the symbolic approaches it had inherited from
AI, and toward methods and models borrowed from statistics, fuzzy logic, and probability theory.[
 Data mining[edit]
Machine learning and data mining often employ the same methods and overlap significantly, but while machine learning
focuses on prediction, based on known properties learned from the training data, data mining focuses on the discovery of
(previously) unknown properties in the data (this is the analysis step of knowledge discovery in databases). Data mining uses
many machine learning methods, but with different goals; on the other hand, machine learning also employs data mining
methods as "unsupervised learning" or as a preprocessing step to improve learner accuracy. Much of the confusion between
these two research communities (which do often have separate conferences and separate journals, ECML PKDD being a major
exception) comes from the basic assumptions they work with: in machine learning, performance is usually evaluated with
respect to the ability to reproduce known knowledge, while in knowledge discovery and data mining (KDD) the key task is the
discovery of previously unknown knowledge. Evaluated with respect to known knowledge, an uninformed (unsupervised)
method will easily be outperformed by other supervised methods, while in a typical KDD task, supervised methods cannot be
used due to the unavailability of training data.
Machine learning approaches are traditionally divided into three broad categories, which correspond to
learning paradigms, depending on the nature of the "signal" or "feedback" available to the learning system:
•Supervised learning: The computer is presented with example inputs and their desired outputs, given by a "teacher",
and the goal is to learn a general rule that maps inputs to outputs.
•Unsupervised learning: No labels are given to the learning algorithm, leaving it on its own to find structure in its
input. Unsupervised learning can be a goal in itself (discovering hidden patterns in data) or a means towards an end
(feature learning).
•Reinforcement learning: A computer program interacts with a dynamic environment in which it must perform a
certain goal (such as driving a vehicle or playing a game against an opponent). As it navigates its problem space,
the program is provided feedback that's analogous to rewards, which it tries to maximize.[8]
Although each algorithm has advantages and limitations, no single algorithm works for all problems.[
 Cloud computing[1] is the on-demand availability of computer system resources, especially data storage (cloud
storage) and computing power, without direct active management by the user.[2] Large clouds often have
functions distributed over multiple locations, each of which is a data center. Cloud computing relies on sharing of
resources to achieve coherence and typically uses a pay-as-you-go model, which can help in reducing capital
expenses but may also lead to unexpected operating expenses for users.
The United States National Institute of Standards and Technology's definition of cloud computing identifies "five
essential characteristics":
•On-demand self-service. A consumer can unilaterally provision computing capabilities, such as server time and
network storage, as needed automatically without requiring human interaction with each service provider.
•Broad network access. Capabilities are available over the network and accessed through standard mechanisms that
promote use by heterogeneous thin or thick client platforms (e.g., mobile phones, tablets, laptops, and workstations).
•Resource pooling. The provider's computing resources are pooled to serve multiple consumers using a multi-tenant
model, with different physical and virtual resources dynamically assigned and reassigned according to consumer
demand.
•Rapid elasticity. Capabilities can be elastically provisioned and released, in some cases automatically, to scale
rapidly outward and inward commensurate with demand. To the consumer, the capabilities available for provisioning
often appear unlimited and can be appropriated in any quantity at any time.
•Measured service. Cloud systems automatically control and optimize resource use by leveraging a metering
capability at some level of abstraction appropriate to the type of service (e.g., storage, processing, bandwidth, and
active user accounts). Resource usage can be monitored, controlled, and reported, providing transparency for both
the provider and consumer of the utilized service.
 List of clouds
•Amazon Web Services
•Google Cloud
•Microsoft Azure
•OpenStack
•IBM Cloud
•Oracle Cloud
•Adobe Creative Cloud
 Cloud computing is a technology where data and programs are stored and accessed on remote servers hosted on the internet instead of
the local server. It eliminates the need for individuals and businesses to self-manage physical resources themselves, and only pay for
what they use1. Here are some key points about cloud computing:
1.Types of Cloud Computing:
1. Infrastructure as a Service (IaaS): Provides virtualized computing resources over the internet, including servers, storage, and
networking.
2. Platform as a Service (PaaS): Offers a platform for developers to build, deploy, and manage applications without worrying
about infrastructure details.
3. Software as a Service (SaaS): Delivers software applications over the internet, accessible through web browsers.
4. Function as a Service (FaaS): Allows developers to execute code in response to events without managing servers.
2.Benefits of Cloud Computing:
1. Flexibility: Easily scale resources up or down based on demand.
2. Efficiency: Optimize resource utilization and reduce wastage.
3. Security: Cloud providers offer robust security measures.
4. Cost-effectiveness: Pay only for what you use.
3.Deployment Models:
1. Public Cloud: Services are provided by third-party cloud providers and accessible over the internet.
2. Private Cloud: Resources are dedicated to a single organization, often within their own data centers.
3. Hybrid Cloud: Combines public and private clouds, allowing data and applications to move seamlessly between them.
4.Cloud Hosting Models:
1. Infrastructure as a Service (IaaS): Provides virtualized computing resources (servers, storage) on-demand.
2. Platform as a Service (PaaS): Offers a platform for application development and deployment.
3. Software as a Service (SaaS): Delivers software applications directly to users.
 Big data refers to extremely large and diverse collections of structured, unstructured, and semi-structured data
that continue to grow exponentially over time. These datasets are so huge and complex in volume, velocity, and
variety that traditional data management systems cannot store, process, and analyze them effectively 1. Let’s
delve into the details:
1.Definition of Big Data:
1. Volume: Big data encompasses vast amounts of information. It’s not just about gigabytes or terabytes;
we’re talking petabytes and exabytes.
2. Velocity: Data is generated at an unprecedented speed—think real-time streams, social media updates,
sensor data, and more.
3. Variety: Big data comes in various formats: structured (like databases), unstructured (such as text,
images, videos), and semi-structured (like XML or JSON).
2.Advantages of Big Data Solutions:
1. Insights: Using big data, organizations can understand market conditions, customer behaviors, and
internal processes.
2. Personalization: Tracking consumer behavior allows hyper-personalized retail recommendations.
3. Fraud Detection: Analyzing payment patterns against historical data helps detect fraud in real time.
4. Optimization: Combining data from order shipments with traffic insights optimizes last-mile delivery.
5. Healthcare Insights: Unstructured medical data analysis aids treatment development and patient care.
6. Urban Infrastructure: Image and GPS data help detect potholes and improve road maintenance.
3.Google Cloud and Big Data:
1. Google Cloud provides tools and services for managing and analyzing big data.
2. Organizations build their data clouds on Google Cloud to extract maximum value from their data.
 Artificial intelligence (AI) is the intelligence of machines or software, as opposed to the intelligence of other living
beings, primarily of humans. It is a field of study in computer science that develops and studies intelligent machines.
Such machines may be called AIs. AI technology is widely used throughout industry, government, and science.
Some high-profile applications include:
1.Advanced Web Search Engines: Think of Google Search, which uses AI algorithms to provide relevant search
results.
2.Recommendation Systems: Platforms like YouTube, Amazon, and Netflix use AI to suggest personalized
content to users.
3.Voice Assistants: Google Assistant, Siri, and Alexa interact with users via human speech.
4.Self-Driving Cars: Companies like Waymo employ AI for autonomous driving.
5.Generative and Creative Tools: Examples include ChatGPT and AI-generated art.
Artificial Intelligence (AI) can be categorized into different types based on various factors. Let’s explore them:
6.Superhuman Game Play: AI excels in strategy games like chess and Go
1.Weak AI or Narrow AI:
1. Description: Narrow AI is designed to perform specific tasks with intelligence. It operates within a limited
scope and cannot go beyond its predefined capabilities.
2. Examples:
1. Apple Siri: A virtual assistant that responds to voice commands but has a predefined range of functions.
2. IBM’s Watson: Combines expert systems, machine learning, and natural language processing for
specific tasks.
3. Other examples include playing chess, self-driving cars, speech recognition, and image recognition.
2.General AI:
1. Description: General AI aims to perform any intellectual task as efficiently as a human. However, no
system currently exists that fully achieves this level of intelligence.
2. Research Focus: Worldwide researchers are actively working on developing machines with general AI
4.Super AI:
1. Description: Super AI surpasses human intelligence and can outperform humans in cognitive tasks. It
remains a hypothetical concept.
2. Characteristics: Super AI can think, reason, solve puzzles, make judgments, plan, learn, and communicate
independently.
5.Reactive Machines:
3. Description: These basic AI systems react to current scenarios without storing memories or past
experiences.
4. Examples: IBM’s Deep Blue (used for chess) and Google’s AlphaGo.
6.Limited Memory Machines:
5. Description: These machines store past experiences for a short period and use them for decision-making.
6. Example: Self-driving cars, which store recent speed data, distances, and other information to navigate
roads.
 Generative artificial intelligence (generative AI) refers to AI systems capable of creating new data, such as
text, images, or other content, often in response to prompts. These systems learn patterns and structures from
their input training data and then generate new data with similar characteristics12.
Here are some key points about generative AI:
1.Training to Create:
1. Unlike traditional AI models that predict outcomes, generative AI is trained to generate novel content.
2. It learns from existing data and produces new data that resembles the input.
2.Applications:
1. Generative AI has a wide range of applications across various industries, including:
1. Software Development
2. Healthcare
3. Finance
4. Entertainment
5. Customer Service
6. Sales and Marketing
7. Art and Writing
8. Fashion
9. Product Design
3.Concerns and Challenges:
1. While generative AI offers immense potential, there are concerns about its misuse:
1. Cybercrime
2. Fake News and Deepfakes
3. Job Displacement
1.Discriminative AI:
1. Objective: Discriminative models focus on classifying existing data into predefined categories.
2. Conditional Probability Estimation: They estimate the conditional probability of a class given input features.
3. Examples:
1. Logistic Regression: Predicts binary outcomes based on input features.
2. Support Vector Machines (SVM): Separates data points into different classes.
3. Deep Learning Classifiers: Neural networks used for image recognition, sentiment analysis, etc.
4. Advantages: Efficient for classification tasks.
5. Limitations: Doesn’t model the full data distribution; may not handle missing data well.
 Algorithmic trading, also known as automated trading, black-box trading, or algo-trading, is a process where a computer program
follows a defined set of instructions (an algorithm) to execute trades. Unlike human traders, algorithmic trading operates at a speed and
frequency that is impossible for manual trading. Here are the key points about algorithmic trading:
1.How It Works:
1. Algorithmic trading combines computer programming and financial markets to execute trades at precise moments.
2. It aims to strip emotions out of trades, ensures efficient execution, and may lower trading fees.
3. Common trading strategies include trend-following, arbitrage, and index fund rebalancing.
4. Algorithms can be based on timing, price, quantity, or any mathematical model.
5. Trades can be executed based on volume-weighted average price or time-weighted average price.
2.Example:
1. Suppose a trader follows these simple criteria:
1. Buy 50 shares of a stock when its 50-day moving average goes above the 200-day moving average.
2. Sell shares of the stock when its 50-day moving average goes below the 200-day moving average.
2. A computer program will automatically monitor the stock price and moving average indicators, placing buy and sell orders when
conditions are met.
3.Advantages:
1. Best Execution: Trades are executed at the best possible prices.
2. Low Latency: Instant and accurate order placement.
3. Reduced Transaction Costs: Efficiently timed trades.
4. No Human Error: Avoids manual mistakes influenced by emotions.
5. Backtesting: Algo-trading can be backtested using historical and real-time data.
4.Disadvantages:
1. Complexity: Developing effective algorithms requires expertise.
2. Market Risks: Algorithms can malfunction or react unexpectedly.
3. Regulatory Challenges: Compliance with market regulations.
4. Data Dependency: Algorithms rely on quality data.
 Smart regulation is a concept that aims to enhance the effectiveness and efficiency of environmental
policies by embracing flexible, imaginative, and innovative forms of social control. Let’s delve into the
details:
1.Regulatory Pluralism: Smart regulation recognizes that traditional command-and-control regulation alone
is insufficient to address complex environmental challenges. It advocates for a broader range of policy
tools, including economic instruments, self-regulation, and information-based strategies. This approach
involves multiple regulatory actors beyond just government and business.
2.Broader Regulatory Influences: Beyond the traditional regulator-regulated dichotomy, smart regulation
considers various influences and interactions:
1. International Standards Organizations: These play a role in shaping regulations.
2. Trading Partners and Supply Chains: Influence behavior through market dynamics.
3. Industry Associations and Peer Pressure: Encourage self-regulation.
4. Internal Environmental Management Systems: Shape organizational culture.
5. Civil Society: NGOs and other groups contribute to regulatory outcomes.
3.Design Principles:
1. Complementary Instruments: Use a mix of policy tools tailored to specific environmental issues.
2. Multiple Participants: Involve governments, businesses, NGOs, and other stakeholders.
3. Adaptability: Be flexible and responsive to changing circumstances.
4. Efficiency and Effectiveness: Strive for better outcomes.
Smart regulation emerged as an alternative to both rigid regulation and laissez-faire market approaches,
recognizing the need for innovative solutions in a complex world.
 Command-and-Control
Aspect Smart Regulation
(CAC)
Flexible, adaptive, and Prescriptive, top-down,
Approach
innovative one-size-fits-all
Mix of instruments, Mandatory standards,
Policy Tools
performance-based permits, penalties
Stakeholder Multi-stakeholder, Limited input, less
Engagement participatory collaboration
Dynamic, risk-based, Static rules, slow to
Adaptability
evidence-driven adapt
Balances costs and
High compliance costs,
Cost-Effectiveness benefits, encourages
rigid requirements
innovation
 Certainly! Here are some examples of smart regulation:
1.Impact Assessments and Evaluation:
1. Thorough Assessment: Major initiatives undergo rigorous impact assessments, evaluating economic, social, and
environmental aspects1.
2. Roadmaps: Detailed information about forthcoming initiatives is available online1.
3. Policy Evaluation (Fitness Checks): Identifies excessive burdens, overlaps, gaps, and obsolete measures1.
2.Stakeholder Engagement:
1. Multi-Stakeholder Approach: Engages businesses, NGOs, communities, and experts1.
2. Extended Consultation Period: Consultation periods for new policy initiatives are extended from 8 to 12 weeks1.
3. Improving Social Impact Assessment: More analysis within the integrated approach, considering distributive impacts1.
3.Simplification and Reducing Red Tape:
1. Simplification Proposals: Over 150 simplification proposals since 2005, including repeal of outdated provisions and
codification1.
2. Cutting Red Tape: Measures proposed by the Commission aim to reduce red tape by more than 30%1.
4.Innovative Approaches:
1. Legal Experimentation: Testing new regulatory approaches.
2. Openness of Legal Framework: Making laws and regulations accessible.
3. Smart Technologies: Leveraging blockchain, smart contracts, and autonomous vehicles23.
5.Regulatory Pluralism:
1. Self-Regulation and Co-Regulation: Involving commercial interests and NGOs as regulatory surrogates4.
2. Flexible and Adaptive Strategies: Beyond rigid rules, embracing creativity and diverse solutions.
Remember, smart regulation aims to enhance policy effectiveness, involve various actors, and adapt to complex challenges in a
dynamic world1.
 Businesses play a crucial role in the successful implementation of smart regulations. Let’s explore how they
contribute:
1.Compliance and Adaptation:
1. Understanding Regulations: Businesses need to comprehend the regulatory landscape, including new
policies and changes.
2. Adapting Operations: They must align their practices with evolving regulations, ensuring compliance.
2.Innovation and Efficiency:
1. Balancing Compliance and Innovation: Smart regulations encourage innovation while safeguarding
public interests.
2. Efficient Processes: Businesses should adopt streamlined processes that meet regulatory requirements
effectively.
3.Stakeholder Engagement:
1. Collaboration: Engaging with regulators, industry peers, and civil society organizations.
2. Feedback Loop: Providing insights to improve regulations based on practical experiences.
4.Risk Management:
1. Identifying Risks: Assessing risks associated with non-compliance or inadequate adherence.
2. Mitigation Strategies: Developing plans to manage risks effectively.
5.Transparency and Reporting:
1. Transparent Practices: Businesses should maintain transparency in their operations.
2. Accurate Reporting: Timely and accurate reporting ensures compliance.
6.Advocacy and Participation:
1. Advocating for Smart Policies: Businesses can actively support well-designed regulations.