Big social problems

  • 6 notes

Social problems I've looked into during high school

Problem 1Food expiration date labels (memo) [note-0017]

by: Saeed Tamboli, Juky Chen Wei Ling, noesis • 2022-10-23

💡 Problem statement: Food labels are wildly inaccurate - The labels are meant to portray when the product is at its peak of freshness, not when it goes bad. Due to this misconception over 90% of Americans throw out food prematurely.

Fundamental food handling inefficiencies cause hunger

Our world is only getting bigger, and that means that we have more and more mouths to feed. If we want to ensure that everyone is able to have the basic necessities to survive we can’t be wasting our food. Food waste is becoming a nearly billion ton problem, with the United Nations Environment Programme's 2021 Food Waste Index stating that an estimated 931 million tonnes of food is thrown away each year. One major contributing factor for wastage of food within the United States, 3rd largest food wasted, are misleading expiration dates.

Facts for context

  • A full third of the food produced in the U.S. is wasted due to consumers’ confusion over labeling
  • This problem is only getting worse with Harvard Food Law and the Natural Resources Defense Council referring to date labels as “a key cause of the high and rising rates of waste in the United States”.
  • Walmart surveyed its private label suppliers and found that they were using as many as 47 different kinds of date labels.
  • The main cause of this is because the companies don’t benefit from making the labels clearer. If the consumer eats the food by that time on the label then they have the best experience possible thus increasing the likelihood of them re-purchasing their product OR if the consumer throws it out then they are inclined to re-purchase the product and make more money.

The outcomes

  • By only preventing waste of meat alone, of the 263 million tonnes of meat produced globally, over 20% is lost or wasted, we can prevent 60 million tonnes of meat going to waste.
  • If we expand to more food items we can save over 130 billion meals and more than $408 billion each year within the United States alone.
  • We can also save more water, land, labor, and energy thus leading to a lower carbon footprint. It also reduces the amount of greenhouse gasses produced, with Municipal solid waste landfill accounting for approximately 14.1 percent greenhouse gasses in america.

• • •

Key innovations allow for new change

  • Paper-based microfluidics is the branch of microfluidics involving devices made out of paper, or other porous membranes, that wick fluids by capillary action. Paper-based microfluidic devices have several advantages over conventional microfluidic devices including simpler fabrication, lower cost, easier disposal, and the ability to operate without pumps or other supporting equipment.
  • Microfluidic system. Locates pathogen by allowing its growth (over multiple hours) that triggers a dye. Best works with liquids such as milk.
  • Electrochemical Biosensors detect compounds that are associated with bacteria.
  • MIT has found silk based and edible sensors effective for solid foods (meat, vegetables etc.). Still requires ~16 hrs to make a prediction using microneedles and bioinks.
  • Bioink responds to pH changes associated with bacteria spoilage.

Four barriers to viability

  1. These colourimetric sensors are not yet mass produced due to an unoptimized manufacturing process.
  2. In particular, there is no standardization of indicator spots. Most existing ones can only be comprehended by academics.
  3. There is also limited integration with existing food packaging.
  4. Limited products have been tested.

• • •

🎯 Our solution: Give consumers stickers they can put on the food to determine whether decay has occurred. Companies would also place these stickers into their meat products.

Visualizing bacteria byproducts to indicate spoiling

  • Bacteria breed on the meat surface, leaving gaseous by-products called Volatile Organic Compounds. This has two stages: First, bacteria break down sugar in the process of catabolism to release alcohol and acids. This lowers the meat’s initially-neutral pH value.
  • Next, when the sugar is depleted, bacteria attack proteins and release amines and thiols.
  • There is one circle to indicate the progress within each stage, respectively.
  • These circles are created by hole-punching Color Catchers, which are papers capable of absorbing run-off colors immediately, into 2 small circles. (Diameter = 0.4cm).
  • Circle #1 is immersed in bromocresol purple (BCP) for 2h. It changes from purple to yellow as the pH decreases from 7.5 to 5.5.
  • Circle #2 is immersed into ellman’s reagent. It turns yellow to reflect the amount of thiols. They are left to dry for 24 hours.
  • Both circles are placed onto the tape to adhere to the meat.

Consumer-end product

Achieving economic viability by catering to all stakeholders

  • Since most companies benefit from the food waste. However, if companies are able to implement this then they will have a marketing edge over their customers and be associated with a higher quality and more responsible product..
  • There is also an incentive for the government to pass legislation to implement this solution universally since it would allow for less money to be spent on garbage disposal and management. Additionally redistribution of possibly wasted food alleviates food security costs e.g. food banks etc.
  • There is a consumer based incentive to transfer over to clearer labels as consumers lose out financially to wasted food that they've bought. This also has an economic benefit on companies who may be prompted by demand posed by consumers.

Problem 2Low quality education in Africa (memo) [note-0029]

by: Aayush Grover, Surya Sure, noesis • 2022-11-20

2.180% of grade 3 Nigerian students are unable to read a single word.

In comparison, North American grade 3 students are expected to be able to comfortably read and write, as well as begin understanding comprehension and analysis.

That being said, Nigerian students in grade 3 have gone through 3 years of education with absolutely no added value. Not only do these students deal with the opportunity cost associated with going to school in the first place, they’re unable to utilize their educations to escape poverty and properly stimulate the economy.

While lack of accessibility to education in Africa is a large and often brought up problem, lack of quality education is just as important. Despite the fact that many children of primary school age simply can’t access education, many of those who have access to education are still unable to become well-educated contributing members of society due to low-quality education in Africa. Educated or uneducated, the education system in African countries has proven to create a low-quality workforce with many of the population trapped in poverty without the ability to escape out of it.

It’s evident that educational quality is incredibly important in creating a valuable workforce, decreasing unemployment rates, improving quality of life for Africans, and escaping poverty. That being said, why is quality education so inaccessible in this continent?

2.2The main culprit is the lack of proper training for teachers.

Teachers are the centerpiece of a functioning education system. A teacher’s skill determines the quality of the students’ education, as well as whether going to school is worth it given the opportunity cost associated with doing so. In Africa, even the children who have access to school are gaining little value from their education, primarily due to a lack of teacher training.

Many teachers are often absent, as they don’t have incentive to show up due to the severely low wages. Teachers in Africa often work multiple jobs which take priority over teaching, resulting in a high rate of teacher a. Even those who do consistently show up are improperly trained and lack the qualifications to adequately teach students. In fact, studies in countries such as Lesotho, Mozambique and Uganda have found that fewer than half of teachers could score in the top band on a test designed for 12-year-olds. In addition, there is a high amount of understaffing in schools in Africa.

2.3Providing high quality education is an essential part of creating a competent and valuable workforce.

A major outcome of high quality education is a valuable workforce capable of contributing to the economy and the development of these countries. It also significantly reduced the strain on global healthcare systems, as well as the carbon footprints of families. Families are unable to escape the struggles of poverty without a high-quality education while access to it provides them a stepping stone to escape poverty, a profound issue seen in all major African countries.

The growth in the world’s labor market is in Africa. As other parts of the world begin to age, Africa will grow its population and today’s children will be the talent tomorrow’s global companies will be recruiting. In the next 30 years, it is projected that sub-Saharan Africa’s working-age population will increase more than twofold—accounting for 68 percent of the world’s total growth*.* Economists have shown that when controlling for other factors, increasing girls’ and boys’ years of schooling (and the skills they learn while there) has a positive effect on economic growth. Ensuring girls’ secondary education is particularly impactful. An increased workforce also leads to an increase in incomes, growth in economies of Africa’s trading partner

2.3.1High quality education decreases violence

Similarly, especially in countries with large youth populations, equitable education provisions can support political stability by sending the signal that the government is attending to people’s needs and giving people more tools to resolve disputes peacefully. This “pacifying effect” of education, as conflict researchers often refer to it, can help reduce the risk of civil war and the growth of ungovernable territories and safe havens for violent extremism.

2.3.2High quality education promotes health and decreses strain on the global healthcare system.

Furthermore, educated girls and women can better seek and negotiate  life-saving health care for themselves and their children. Global studies have shown increased education—particularly for girls—leads to less infant deaths, less maternal mortality, and less infection from viruses (HIV/AIDs). The evidence is so strong for girls’ education that some health researchers call it a “social vaccine.” Healthier communities mean less strains on health systems, particularly relevant to the global COVID-19 pandemic.

Lastly, educating and empowering women can decrease death rates and displacement due to weather-related disasters, and could result in an estimated 85 gigaton reduction of carbon dioxide by 2050.

2.4African countries simply don’t have the funding necessary to adequately train teachers.

With a significant lack of funding in the healthcare system in African countries, support for trained teachers and adequate training for teachers simply isn’t accessible. The already inadequate education system makes the supply of trained teachers incredibly low. A lack of proper educators contributes to this low-supply of trained teachers, making it incredibly difficult to stimulate a well-developed education system in Africa.

As well as this, one of the major priorities in Africa is to provide access to an education as opposed to a quality education. This means that insufficient funding is allocated into ensuring that education is of a high quality, that students who are being educated are actually literate, and that curriculums are being updated and thoroughly followed to ensure a standard of education for all students in these countries.

This clear lack of funding and defecit in adequately trained teachers is evidently unable to support the large amount of students who require education. At the end of the day, students choosing to persue an education in Africa, if possible, comes with a significant amount of opportunity cost. With the lack of quality of education, many people of primary school age join the workforce to help provide for their family rather than educate themselves in a system that doesn’t necessarily make them educated and contributing members of society.

2.5Teaching at the Right Level (TaLR) focuses on solidifying foundational skills within students.

This organization divides African students from grades 3 -5 into groups based on learning needs rather than age or grade in elementary school to learn reading, writing and counting. It is currently being implemented in Côte d’Ivoire and Zambia. Since 2001, J-PAL-affiliated researchers have rigorously tested the theory of change underlying the TaRL approach. Through 6 randomized evaluations in India, as well as a growing body of research in Africa, they find that when TaRL is successfully implemented, learning outcomes improve.

2.6The Global Partnership for Education promotes gender equality

Focuses on gender equality, as well as teaching quality and assessment, early and inclusive education and education in crisis. This organization was found in 2002 and operates mainly in Burundi, Guinea-Bissau, Lesotho, Mauritania, Sao Tome and Principe.

2.7Coca-Cola Foundation has funded teachers and low-income schools

In 2020, the Coca-Cola Foundation spent $52,725 in funds for teacher training and support for virtual learning in 200 low-income schools in Nigeria. This initiative was found by Roberto Goizuela in 1984. They have a strong presence in all African countries.

2.8Unanswered Questions:
  • How to deliver proper cost-efficient training?
  • How to offer incentives for teacher attendance?
  • How to find more willing teachers?

2.9People to discuss this topic with include:

Rebecca Winthrop - Director for the centre of Universal Education, Senior Fellow at Global Economy and Development. Authored articles for Brookings on improving quality public education in Africa.

Russell Rickford - Expert in African American Education, African-American political culture, history of education and American social movements

Robert S. Peterkin - Expert in education achievement, school reform and African-American cildren, equitable school choice leadership.

Problem 3UN Environmental Programme challenge submission (top 5 out of 40) [note-0043]

by: Aditya Mahes, Noorish Rizvi, Shirley Yang, noesis • 2022-03-24

My team's submission to the United Nations Environmental Programme challenge got top 5 out of 40 competing teams. It was an intense few weeks gathering data, outreaching to experts, resolving team conflicts and prepping for AP exams. Our deliverable is a 27-page slide deck

Problem 4Notes on Senior loneliness in North America and companion robots [note-0049]

by noesis, contributors Colyi Chen and Elena Mishina • 2023-04-14

I looked into senior loneliness, conducted in-person interviews in Waterloo, Canada and pitched the research at a Chinese conference informally, mentioned on technologist Yuquan Wang's podcast. 2023 fall: I wasn't very satisfied with breaking down the problem by personal vs environmental causes. Later I realized social problems often have feedback loops that makes MECE analyses insufficient.

4.1Introduction

Loneliness hits the senior population the hardest, in terms of mental health--increasing the risk of depression and physical health--dementia as well as cardiovascular diseases. In North American, more than 43% of adults over the age of 65 frequently experience loneliness, with seniors accounting for one-tenth of the world’s population.

This also means, if senior loneliness is "perfectly solved", we'd reduce people suffering fromdementia by up to 7 people globally and heart disease by 3.36 million in the US.

4.1.1Subproblem spotlight - inmobility

(noesis) In North America, 4.76 million of community-dwelling seniors are unable to independently leave the house at least once a week, significantly raising the risks of loneliness.

Another way to think about this is that the Individual functional capacity does not meet the demands of the life-space—bedroom, home, outside home, neighborhood, town and distant locations.

This can roughly bebroken down into environmental and personal causes.

4.1.1.1Personal causes of inmobility

Fears, walking barriers and driver's license suspension.

Fear of moving outdoors

Nearly 600,000 older people leave the house once a week or less.

This is fueled by fear of social rejection and falling.

Fear of social rejection

A Canadian survey found 63% of seniors felt they had been treated unfairly based on their age, beliefs, fears and identities. Seniors have an attention bias to aging-reminder words like “senile” or “old” (source). “From the way I have been represented, I don’t want to show my face in public”—John Roberts. Older adults reported greater increases in hurt feelings following rejection than younger adults, contributing to future fears. This is caused by low self-esteem. Psychology says this can be boiled down to an external locus of control, such as learned helplessness (source): ”my grandpa who is 89 just lies on bed and only eat or drink when it’s time, but only a small portion. But he does post poems on Facebook”—Quora user. However, many don’t have a healthy outlet, feeling physically, mentally and emotionally confined to deal with lack of control. Sometimes, seniors who require care experience angry outbursts because they don’t have the freedom to control where they go (source).

Fear of falling

About 20–60 % of community-dwelling older adults have fear of falling, and 20–55 % report limited daily activities due to fear of falling. Falls result in deterioration of physical functioning. and quality of life. studies have found that senior citizens with a fall history have a FOF prevalence of 40–73%. One-third of people over 65 will fall at least once a year. Among Canadian seniors, falls remain the leading cause of injury-related hospitalizations, and absolute numbers are on the rise (source))

Even if 7/12 million community-dwelling seniors adopt anti-fall devices, they can turn into fall-encouragement devices without adequate repair. For example, cane tips can become worn, wheels on walkers and wheelchairs can become loose, or equipment can be too heavy or the wrong height. Attitudes about devices aren’t well-known, but in the seniors without devices, some claim to have no need, some avoid it due to stigma, and some due to fear of dependence and lack of training(source).

Walking barrier

30% of seniors report that walking three city blocks or climbing one flight of stairs are major physical challenges(source). 28% reported difficulty and 17% inability to walk 1/4 mile at baseline. The main physical risk factors disabling seniors from walking are neuromuscular and sensory system deterioration.

Aging affects muscle mass and strength, bone density, and can make joints stiffer due to reduction of cartilage thickness. 5 - 10% of seniors suffer from vision impairment and 27% suffer from moderate hearing loss. Additionally people with both vision and hearing impairments had over four-fold risk, and people with co-existing impairments in vision, hearing and balance almost 30-fold risk for falls during walking. The ability to walk is an underutilized predictor for mental and physical health, mortality and hospitalization.

Drivers’ license suspension

Seniors’ driving license can be suspended by physicians or the police, while a study found that only 10% of suspended drivers are unfit to drive (source), which causes significant frustration. Research suggests that reductions in the time spent driving are not balanced with an increase in the time spent as a passenger in an automobile or walking(source).

Automobile was the only reliable method of transportation for the 35% of seniors living in small towns and rural areas in Canada. Thus, driving cessation is linked to a decline in out-of-home activity levels and feelings of isolation.

I lost my drivers license—I thought to myself, I can’t live another winter like this”—Senior once living in rural Ontario, Canada.

Never thought of not having a car, never crossed my mind. When you can't go out and get in your car and go where you want to go, it's like having your arm cut off.”—Senior in Ontario, Canada

It's been demonstrated and said many times, that receiving the news that you will be losing your driver's licence has the same weight as being diagnosed with cancer”—Sylvain Gagnon, researcher at CANDRIVE.

4.1.1.2Environmental causes of inmobility

Lack of public transport

Among the 35% of seniors (Canada) living in rural areas, there are rarely any public transportation, causing a greater risk of isolation from their friends, local community activities and health and social services.

Dangers

Even if there is public transport, the environment’s unsafe design—from uneven side-walks, curbs, noise, heavy traffic, inadequate lighting, lack of resting places, sloping terrain, long distances to services and weather conditions presents risks for seniors to travel outside (source).

The government is slow to react to aging population to establish changes, therefore change must start from within.

Root cause analysis

4.2Solutions

The main buckets we looked into are mobility hardware, mobility software and combinations.

4.2.1Software for mobility.

(Elena) a. BrioCare is a new, voice-assistant technology solution.

  • Similar to Alexa and Siri in operation
  • Engages the mind and body of seniors throughout the day; beginning with a greeting in the morning, to asking what they would like to do during the day, and finally ending with their nightly routine

b. CaringWire is a digital platform that makes healthcare more accessible and manageable for individuals and families.

c. Birdie is a holistic care platform providing tailored preventive care for older adults so they can live independently in their own homes.

  • Uses apps and home connected devices to track elderly well-being in real-time.
  • It has also developed healthcare analytics using data from carers’ reports and connected sensors to deliver better preventative care

Main limitations:

a. BrioCare

  • Its services are limited for only voice-based help
  • Cannot help elderlies with mobility issues outside of their houses

b. CaringWire

  • Although it provides the medical assistance, it doesn't help in moving in and out of the house - the service that seniors with lack of mobility really need

c. Birdie

  • Act as a virtual assistants but lack physical help in managing household chores, etc.

4.2.1.1Mobility hardware.

(Elena) a. Best Mobility Aids sells mobility aids available, including mobility scooters, rollators, walking frames, and other assistive technologies.

b. Sedimentum is a company of save-living apps that warns families of any casualties of seniors when they're alone in their homes

  • In in the SAFE-living app the emergency contacts (e.g., neighbours or relatives) are defined.
  • The app also offers other features, such as a digital SOS emergency button with GPS for on the go.

c. NavChair is a navigation and autopilot system which enables them to avoid obstacles along their route.

  • Can find a step-free route to make sure user's needs are met

Main limitations:

a. Best Mobility Aids

  • Have a pretty complex operations systems that would be hard to wear by themselves for seniors
  • Cost devices and technologies that not all family with elderlies can afford

b. Sedimentum

  • Do not provide necessary help for seniors for going shopping or going to parks

c. NavChair

  • Not really good for people who live in closed off areas or areas with bad roads infrastructure

4.2.2Companion robots.

These companies offer a combination of software and hardware solutions for senior mobility.

  1. Top companies:
    1. Intuition Robotics - The main product is ElliQ.
    2. AIST - PARO
    3. SoftBank Robotics - Pepper
  2. Main limitations:
    1. ElliQ
      • unable to move
      • applies a singular proactive solution to seniors with varying needs of companionship
      • some have problem adopting the humanizing form and think it’s patronizing (source)
      • mashing together a large number of underdeveloped features: (1) Despite highlighting the ability to initiate conversations, most last 2 sentences or less, even less than existing digital chatbots. (2) It could play videos and songs from a database, but lacks flexible integrations with youtube, spotify etc. (3) It has no established system of contacting emergency services. There are also implementation limitations like video call lagging, speaker glitches and delays. It’s one time payment and monthly costs higher than medical alert systems. Some users reported feeling dystopian vibes(source)
    2. PARO
      • One survey found 1 in 10 refused to interact with PARO in front of others since they felt it was childlike or had previous negative experiences with animals
      • PARO does not have any voice recognition for calling 911 or a method to report falls, which may cause anxiety in some seniors living at home.
    3. Pepper
      • Appearing like humans prompts people to ask questions it can’t answer
      • It was a master of none, failing at the first step of interaction: face, emotion and voice recognition. Leading to the subsequent lack of trust.
    • Buddy
      • mishears commands, repeats same phrase “I’m tired to talk”

4.2.2.1The backdrop of companion robot startups

(noesis)

  1. Intuition Robotics, founded 2015 elliq
    1. Team: Founders: Dor Skuler, Itai Mendelsohn, Roy Amir. Has 50 - 100 employees.
    2. Money raised: Raised a total of $58 million from over 5 rounds. Their latest funding was raised on Feb 13, 2020 in a Series B round.
    3. Markets served: Launched in 2018. US and other English-speaking countries, plan to expand into Japan
    4. Impact to date: According to the 2022 impact report, ElliQ both reduces loneliness for 80% of users and helps 82% stay mentally active. At least 800 seniors have been impacted in a partnership with New York State Office for the Aging, but the exact number is not known since it is a private company.
    5. Solution: ElliQ includes a physical voice assistant and a tablet with software. The physical assistant is like Alexa; The main difference being it engages seniors without prompting. It includes a camera and it’s head can also move back and forth. Together with the software it supports four categories of use:
      1. Companionship/Entertainment: Can initiate conversation and remember things about users, searches through existing database of resources of jokes, videos, etc.
      2. Health and Wellbeing: Can show training videos in the database for mental and physical health
      3. Connecting to acquaintances: video calling
      4. Practical: Daily reminders, alarms etc can be spoken and displayed on the tablet.

2.Japan National Institute of Advanced Industrial Science and Technology (AIST) - 2004 paro 1. Team: Created by Japanese engineer Takanori Shibata
2. Money raised: subsidized by the Japanese government
3. Markets served: More than 30 countries including Japan, Canada, US, and various countries in Europe serving in hospitals, nursing homes and private homes
4. Impact to date: More than 10 000 PAROs are distributed worldwide. Studies found the main benefits are reducing negative behaviours—agitation and falling risks, improved social confidence and rates of seniors, and promoting positive mood.
5. Solution: PARO is a smart stuffed animal—The Therapeutic Seal gathers data through five types of sensors: touch, light, motion, temperature and posture sensors. It detects patterns through its proprietary AI and machine learning algorithm to then reply using animal sounds and motion.

  1. SoftBank Robotics Holdings - Pepper pepper
    1. Team: Founded by Masayoshi Son
    2. Money raised: 236 Million, venture series unknown
    3. Markets served: list countries or regions for market
    4. Impact to date: # of products sold, or people impacted
    5. Solution: Pepper is a mobile and adorable robot aiming to proactively start conversations. Users can interact with Pepper through face recognition, touch sensors, LED, speaking and tapping on the tablet. It’s presence allowed an opportunity for a social event, the interaction showed interest in older people’s lives and increased self-esteem, with exceptions of talking about their children. Flaws perceived as empathetic. The only negative comments were on the speech speed and the lack of pauses.

4.2.3Studies on companion robots

In the recent decade, studies showed that companion robots can help seniors reduce feelings of isolation. After accompaniment, seniors enjoyed the availability and non-judgemental attitude of these robots. They treated the robots as friends, became more facially expressive and felt generally more positive over the long term.

  • A cross-sectional study of the effects of COVID-19 on perception of and intention to purchase a social robot found that loneliness was positively associated with reported willingness to buy a robotic companion, indicating that people may perceive that a robotic companion could mitigate loneliness.

  • A study that predates the pandemic of non-AI robots, Paro and Giraff (telepresence), suggests a role for psychosocial functioning (depressive mood, loneliness, life satisfaction and social support) in robot acceptance among older adults.

  • A small study of robots use in dementia care found that participants were concerned that it could increase isolation for this group.

Companion robots also benefit, not replace, human interaction: Accompanied seniors formed more new connections, and had more conversations with family and other human beings.

While well-intentioned, current designs like ElliQ, ROBEAR and SAM heavily involve rubber and plastic. According to surveys, seniors view such materials as "too cold". It is also unfavourable for robots to resemble toys or humans; be too small; be too fast-moving; be noisy and be a hassle to maintain.

Meanwhile, seniors felt close to robots which look like familiar animals with soft fur, facial expressions, voice and breathing movements.

Companion robot market size estimated to be $9.2 billion USD and expected to expand to $36.3 billion USD by 2028. Financially viable, but will likely be expensive to compensate for costs. Hence, market to middle-upper class in developed countries.

4.2.4How companion robots work

pipeline The speech recognition module generates several hypotheses of the uttered phrase ranked in terms of confidence in the N-best algorithm. Text from the first-best is passed into the Natural Language Understanding (NLU) system into symbolic language. e.g. ``a red cup = cup(x) ^ red(x)``. While not every robot converts to symbolic language, social robots which rely on advanced logic would use both first-order predicate logic and temporal logic, e.g. grabApple = False and becomes ``True`` later to reflect the changes across time.

Using perceptions, the robot connects the world representation and the symbolic representation together. Decision-making uses the memory of the conversation and the user environment to decide the next physical or language action. Language action is converted back into the natural language generation module and finally uttered by the text-to-speech system.

NLU you say? What does that mean?

NLU overview: types of language models Language models aim to create a probability distribution over the future/missing tokens.

Statistical language models (SLMs)
This is based on the Markov assumption, which states that the probability of a word depends only on a limited number of preceding words (i.e., fixed-context). SLMs and uses a number of words before the last word to predict the most statistically likely next word. An n-gram language model is a type of SLM that models the probability of a word given the last n−1 words. A bigram model (n=2) considers only the previous word (hence two words in total), while a trigram model (n=3) considers the previous two words.

However, SLMs suffer from the curse of dimensionality: As the number of features (e.g. vocab, punctuation, num words) in the input increases, the amount of possible n-grams required to accurately model the probability also increases exponentially. This leads to data sparsity, meaning that many word sequences are not observed in the training data, making probability estimation unreliable. Thus, performance degrades.

  • training: many n-grams
  • prompt: a specific n-gram
  • output: probability distribution over next possible words

Neural Language Models.
Data is passed into a neural network. Each word is assigned a vector of continuous values, with the dimensions of the vector representing different features of the word. The idea is that words with similar meanings will have similar vector representations, the vector for the word "king" might be located near the vector for "queen”. Approaches like Continuous Bag-of-Words or Skip-gram is used to represent the relation between words. Continuous Bag-of-Words (CBOW): In this approach, the neural network predicts the current word based on the context words surrounding it. The context words are represented as a bag of word embeddings, which are learned during training. The bag of embeddings is then averaged to create a fixed-size vector, which is passed into a neural network to predict the target word. Skip-gram: In this approach, the neural network predicts the context words based on the current word. The current word is represented as a word embedding, which is learned during training. The word embedding is then passed into a neural network to predict the context words. The set of vectors and their geometric relationships are passed into Neural Network to predict the probability. The network contains of an input, hidden and an output layer. word2vec is a relatively effective model.

  • training: millions ~ billions of words.
  • prompt: word sequence of arbitrary length
  • output: word sequence of arbitrary length

Types of deep neural networks used: LSTMs, Transformers, Bidirectional transformers.

Large Language Models As of 2023, most large language models can take in 4,000 words, with the largest taking in 32,000 words.

Word and sentence embeddings. Embeddings can capture analogies well. Each word is assigned some properties that are placed on an axis. e.g. The word dog can be assigned the properties age and size, and is plotted as a point in nth dimensional space based on num properties. This can also be applied on the sentence level. These features are found by the computer and can sometimes be interpreted by a human.

How similarity is measured:

  • Dot product. The dot product between two items is calculated across each column. A large number signifies similarity.
  • Cosine distance: Take the angle difference between the position vectors. Then take cosine. Similarity ranges from -1 to 1 (itself) Can evaluate similarity between queries and answers to discover the right answer.

Some terminology:

  • Encoder-decoder models, i.e., sequence-to-sequence models areGood for generative tasks that require an input, such as translation or summarization.
  • Encoder-only models are good for tasks that require understanding of the input, such as sentence classification and named entity recognition.
  • Decoder-only models: Good for generative tasks such as text generation.

[30 lines regarding attention mechanisms omitted since they're common knowledge anyway and poor formatting]

4.2.5Ideas on building a companion robot?

First you can code a digital prototype. Play around with convai, character.ai, replika and so on. The user could speak vocally about how their day is going, ask for social support, or muse about the philosophy of life. Then, the companion speaks back to them with animated expressions. The text response will be generated with some LLM and read aloud. Meanwhile, the tone of the text will be analyzed to display the right animations. This should take no longer than two weeks to implement.

Next, build the physical prototype. Find a manufacturer that makes children's stuffed animals, go around in Shenzhen and you'll find a bunch. The previous program will be downloaded into a single-board computer inside the robot. Several new functions are needed: Firstly, generating facial expressions. Secondly, moving animal parts for realism. Thirdly, controlling breathing, by using a linear actuator to inflate or deflate a ball inside the robot - try Pikachu!

A report by Tractica estimates that by 2025, there will be over 33 million social robots deployed worldwide, up from just 3.1 million in 2016. This growth is driven by advancements in artificial intelligence and natural language processing technologies.

4.2.6Readings for companion robots

last updated spring 2023

The Handbook on Socially Interactive Agents: 20 years of Research on Embodied Conversational Agents, Intelligent Virtual Agents, and Social Robotics Volume 1: Methods, Behavior, Cognition

A list of recommendations for social robots

LLM and robotics content list

Improving the logic of NLU

Review on Multiple types of companion robot

Hobbit robot for seniors living independently

Robots using language

Emotional support for conversations

Analyzing social robotics with NLP

NLG evaluation

Memory

ConvAI competition ConvAI research Hugging Face

Problem 5Domestic violence statistics [note-0062]

compiled in 45 minutes.

He holds me after breaking me, whispering that he never meant to, as if his regret could unmake the ruins of me. I wonder how much blood a body can lose before it stops calling itself alive.

1 in 3 women and 1 in 4 men have experienced some form of physical violence by an intimate partner. This includes a range of behaviours, including light as pushing, shoving, and slapping. In some cases, this might not be considered "domestic violence." 1 in 7 women and 1 in 25 men have been injured by an intimate partner.

Estimates published by the World Health organization indicate that globally about 1 in 3 (30%) of women worldwide have been subjected to either physical and/or sexual intimate partner violence or non-partner sexual violence in their lifetime.

Nearly 20 people/minute are physically abused by an intimate partner in the United States. During one year, this adds up to more than 10 million women and men.

More than one in six married women in each country that was studied reported being pushed, shaken, slapped, or targeted with a thrown object by their male partners. At least one in 10 has been threatened or publicly humiliated by their husbands. 42% of women who experience intimate partner violence reporting an injury as a consequence of this violence.

Country-specific

The percentages of women who said an intimate partner had ever abused them ranged from 48 percent in Zambia and 44 percent in Colombia to 18 percent in Cambodia and 19 percent in India. (A 1998 Commonwealth Fund study put levels of similar violence in the United States at 31 percent).

Impact on children

  • Almost one-third of children in low-income and lower-middle-income countries have been exposed to IPV (intimate partner) in their lifetime
  • Children who grow up in families where there is violence may suffer a range of behavioural and emotional disturbances. These can also be associated with perpetrating or experiencing violence later in life.
  • Intimate partner violence has also been associated with higher rates of infant and child mortality and morbidity (through, for example diarrhoeal disease or malnutrition and lower immunization rates).

Problem 6Food waste - The overstocking problem (memo) [note-0040]

  • 10-27-2022
  • Mansi Katarey, Serjan Kaur, Surya Sure, noesis
  • #food-waste

💡 Problem Statement: $50 billion dollars are lost each year in the US due to the overstocking problem. The surplus of goods without corresponding demand results in food wastage.

6.1Executive Summary

  1. Overstocking is caused by misjudged consumer demand

    Due to inability to accurately predict consumer demand, retailers in the food produce industry constantly overstock to prevent “selling out”. This method results in constant food wastage.

  2. Existing demand forecasting models are not scalable and inaccurate

    Innovative forecasting algorithms have only been tested in Russian regions, supports large businesses and doesn’t yet support automation. Meanwhile conventional forecasting software have only been tested in a few states.

  3. Integrating a conventional and experimental model could reduce US food waste by over 30%

    Afresh technologies provides a baseline forecasting model based on Machine Learning with over 600 parameters affecting demand within US. The core algorithm can be enhanced with more accurate machine learning techniques from DSLab, based in Russia.

6.2The Problem: Overstocking

Overstocking is a $50 billion problem in today’s world. It is a common belief amongst the grocery produce industry that over-stocking will be more beneficial to the company rather than under stocking. This is because retailers can't afford to risk losing sales because they ran out of stock. Within this, fresh products accounting for up to 40 percent of grocers’ revenue and shelf life of 1 to 7 days.

Only large grocery stores have forecasting methods despite way more small grocery stores: There are only 21000 large businesses within the US while 32.5 million small businesses exist. However, fresh products are more difficult to predict than stock items.

6.3The Root Causes: Supply and Demand, Supply Chain and Farmers

Fear of going out of stock

Out-of-stocks cost retailers $1 trillion yearly. The consequences of out-of-stocks are severe, from losing profits to losing customers and inevitably market share. The direct and indirect damages of lost sales are so great that retailers prefer to markdown unsold inventory, or even get rid of it at cost.

Poor inventory management

New inventory can be acquired without accurate data showing your profit margins and cost of goods sold. This information is key to beginning proper inventory management and avoiding overstocking.

Sudden change in consumer patterns

With the demand of certain produce changing on a regular basis, it becomes difficult to judge the consumer demand. This change can be due to latest food trends, economic change, weather, etc.

During COVID, there was an increase in the number of people who couldn't afford groceries and a surplus of food where it wasn't needed. Some of the most popular destinations, such as chain restaurants, schools, and workplace cafeterias are struggling to adapt.

6.4Current solutions: Additional training, partnerships, consumer education and forecasting models

Walmart Canada

Walmart has been undertaking waste-reduction initiatives since 2005. Between 2015 and 2017 alone, Walmart Canada reduced food waste in its operations by 25%.

  • Discounting repackaged bruised or peak-freshness products through a $1/$2 Bag Program and reducing prices on fresh meat, bakery, dairy and produce approaching best before dates.
  • Reducing over-production in bakery operations. Providing additional processes, training and resources to help support associates.
  • Implementing organic recycling programs in stores and distribution centres that take unsaleable and unsold food for conversion into animal feed, compost and energy.
  • Partnering with local food banks to assist in maximizing surplus food donations.
  • Working with suppliers to improve packaging and food handling processes to maintain quality and freshness.

Harvard Business Review

A December 2017 Harvard Business Review article, How Large Food Retailers Can Help Solve the Food Waste Crisis, presents a four-pronged strategy to help retailers reduce food waste throughout the supply chain, from farming and production to stores and end use.

  • Upgrade inventory systems with the latest technology. Examples include software that helps retailers streamline deliveries from the warehouse to the store; or programs that reduce excess inventory and handling.
  • Partner with farmers in the supply chain. Retailers are encouraged to share forecast data for specific food items to prevent overplanting.
  • Modify or eliminate store practices that increase waste. For example, discounting “imperfect-looking” produce or donating surplus edible food to charities.
  • Educating consumers to cut household waste. Content shared with customers can go a long way toward helping them understand the issues around food waste and the ways the industry is working to alleviate the problem.

Afresh Technologies

  • Afresh offers an operating system that helps grocers reduce the amount of fresh food that is thrown away. Retailers can view their inventory within Afresh’s system and use its technology to more accurately forecast what foods consumers are looking to buy. The predictive system’s reliance on data means stores will produce less waste.
  • Its algorithms also factor in the intangibles like weather and peak freshness of produce to help predict demand and manage inventory.
  • Afresh says it helps customers reduce waste by 25% or more. These efforts can also improve profitability
  • The company has announced partnerships with grocers in more than 3,000 stores across 40 states
  • Company’s total funding has reached $148 million.

6.5Gaps: Lack of Integrated and Accurate Forecasting Models.

Operational Limitations

There is not yet an accurate forecasting model spanning all states. Afresh only has expanded to 17 states. Meanwhile, accurate forecasting software has only been tested locally such as in Russian retail stores and in canteens. The software are not yet automated into the demand forecasting. Similarly, the top influencing factors need to be identified to provide consumers with ease of insight. Data should be generated at the store level.

Technological Limitations

Existing forecasting algorithms require massive volume of training data to yield accurate results, rendering the model unusable for small grocery stores. Existing forecasting algorithms for fresh food usually deliver a median forecast i.e. How many items will be sold in the future? A single number doesn’t allow grocers to adjust to the shifting market values.

6.6Solution: Combining optimized forecasting algorithms with existing models

Hypothesis

If we combine the forecasting technology used at Afresh with novel algorithms developed by DSLab based in Russia, food waste will decrease by over 30% in grocery stores across the US.

Solution overview:

  • Our solution uses efficient machine learning to identify the relationship between more than 600 variables and the demand of products. Sample internal factors include: weekly data of purchasing, variability of demand with promotions and shelf life of product. External factors include: weather, large football games or concerts.
  • Machine-learning algorithms that stem from gradient boosting over decision trees are used to obtain highly accurate predictions,
  • Rather than a single future amount, the Bayesian method is used to output ranges of future demand e.g. 90% confidence that 300 broccolis will be sold on Tuesday at Costco. 10% confidence that 100 broccolis will be sold.

Why is it better than status quo?

  • This forecasting model takes into account promotions. With 60% of goods being on offer, this is a huge factor in changing demand.
  • This model allows prediction of fresh food with shelf life of 1 - 7 days
  • Machine learning models using Bayesian methods require less training data, meaning this model could also be adapted for small grocery stores, as well as retail which expands regularly.

Feasibility

  • This forecasting method has previously been tested in one of the largest retail chain in Russia—Lenta. The result was 13% higher accuracy compared to existing forecasting.
  • The novel method is developed by an expert team with 10+ years of experience in data analysis, ML and AI in world-leading IT companies
  • There are many studies testing the Bayesian method on the food predictions of canteens. Canteen food are comparable to perishable food in grocery stores.

Unknowns:

  • The policies surrounding demand forecasting may be subject to change within the US.

6.7Outcome: Save over 300 pounds of food every week

Understanding consumer demand is crucial to the reduction of food wastage. Predicting better consumer patterns will enable grocery retailers to make better inventory choices, and determining the amount of produce to order each week. If implemented just within one Walmart store, this could save up to 300 pounds of food every week.

Holistically, this means reducing more than 88.5 Gigatons of CO2 between 2020-2050 which ranks first out of any factor.

6.8Next steps: Determining the generalizability of the forecasting model

Since Afresh technologies is based in the US, the next step would be to expand partnerships to other North American countries.

Each country has patterns of food waste in each supply chain, which need to be determined before replicating Afresh technology’s model to the region.

6.9Sources