Google announced the expansion of its artificial intelligence (AI) flood forecasting system on Monday. With this expansion, the Mountain View-based tech giant will now cover 100 countries and offer...

Since its birth, the stock market has received widespread attention from many scholars and investors. However, there are many factors that affect stock prices, including the company's own internal factors and the impact of external policies. The extent and manner of fundamental impacts also vary, making stock price predictions very difficult. Based on this, this article first introduces the research significance of the stock market prediction framework, and then conducts academic research and analysis on two key sentences of stock market prediction and artificial intelligence in stock market prediction. Then this article proposes a constructive algorithm theory, and finally conducts a simulation comparison experiment and summarises and discusses the experiment. Research results show that the neural network prediction method is more effective in stock market prediction; the minimum training rate is generally 0.9; the agency's expected dilution rate and the published stock market dilution rate are both around 6%.

The supply chains of the Canadian forest products industry are largely dependent on accurate demand forecasts. The USA is the major export market for the Canadian forest products industry, although some Canadian provinces are also exporting forest products to other global markets. However, it is very difficult for each province to develop accurate demand forecasts, given the number of factors determining the demand of the forest products in the global markets. We develop multi-layer feed-forward artificial neural network (ANN) models for demand forecasting of the Canadian forest products industry. We find that the ANN models have lower prediction errors and higher threshold statistics as compared to that of the traditional models for predicting the demand of the Canadian forest products. Accurate future demand forecasts will not only help in improving the short-term profitability of the Canadian forest products industry, but also their long-term competitiveness in the global markets.

To assess a country's economic outlook and achieve higher economic growth, econometric models and prediction techniques are significant tools. Policymakers are always concerned with the correct future estimates of economic variables to take the right economic decisions, design better policies and effectively implement them. Therefore, there is a need to improve the predictive accuracy of the existing models and to use more sophisticated and superior algorithms for accurate forecasting. Deep learning models like recurrent neural networks are considered superior for forecasting as they provide better predictive results as compared to many of the econometric models. Against this backdrop, this paper presents the feasibility of using different deep-learning neural network architectures for trade forecasting. It predicts export trade using different recurrent neural architectures such as 'vanilla recurrent neural network (VRNN)', 'bi-directional long short-term memory network (Bi-LSTM)', 'bi-directional gated recurrent unit (Bi-GRU)' and a hybrid 'bi-directional LSTM and GRU neural network'. The performances of these models are evaluated and compared using different performance metrics such as Mean Square Error (MSE), Mean Absolute Error (MAE) Root Mean Squared Error (RMSE), Root Mean Squared Logarithmic Error (RMSLE) and coefficient of determination <em>R</em>-squared (<em>R</em>²). The results validated the effective export prediction for India.

Aim/Purpose: In the United States, the Centers for Disease Control and Prevention (CDC) tracks the disease activity using data collected from medical practice's on a weekly basis. Collection of data by CDC from medical practices on a weekly basis leads to a lag time of approximately 2 weeks before any viable action can be planned. The 2-week delay problem was addressed in the study by creating machine learning models to predict flu outbreak. Background: The 2-week delay problem was addressed in the study by correlation of the flu trends identified from Twitter data and official flu data from the Centers for Disease Control and Prevention (CDC) in combination with creating a machine learning model using both data sources to predict flu outbreak. Methodology: A quantitative correlational study was performed using a quasi-experimental design. Flu trends from the CDC portal and tweets with mention of flu and influenza from the state of Georgia were used over a period of 22 weeks from December 29, 2019 to May 30, 2020 for this study. Contribution: This research contributed to the body of knowledge by using a simple bag-of-word method for sentiment analysis followed by the combination of CDC and Twitter data to generate a flu prediction model with higher accuracy than using CDC data only. Findings: The study found that (a) there is no correlation between official flu data from CDC and tweets with mention of flu and (b) there is an improvement in the performance of a flu forecasting model based on a machine learning algorithm using both official flu data from CDC and tweets with mention of flu. Recommendations for Practitioners: In this study, it was found that there was no correlation between the official flu data from the CDC and the count of tweets with mention of flu, which is why tweets alone should be used with caution to predict a flu out-break. Based on the findings of this study, social media data can be used as an additional variable to improve the accuracy of flu prediction models. It is also found that fourth order polynomial and support vector regression models offered the best accuracy of flu prediction models. Recommendations for Researchers: Open-source data, such as Twitter feed, can be mined for useful intelligence benefiting society. Machine learning-based prediction models can be improved by adding open-source data to the primary data set. Impact on Society: Key implication of this study for practitioners in the field were to use social media postings to identify neighborhoods and geographic locations affected by seasonal outbreak, such as influenza, which would help reduce the spread of the disease and ultimately lead to containment. Based on the findings of this study, social media data will help health authorities in detecting seasonal outbreaks earlier than just using official CDC channels of disease and illness reporting from physicians and labs thus, empowering health officials to plan their responses swiftly and allocate their resources optimally for the most affected areas. Future Research: A future researcher could use more complex deep learning algorithms, such as Artificial Neural Networks and Recurrent Neural Networks, to evaluate the accuracy of flu outbreak prediction models as compared to the regression models used in this study. A future researcher could apply other sentiment analysis techniques, such as natural language processing and deep learning techniques, to identify context-sensitive emotion, concept extraction, and sarcasm detection for the identification of self-reporting flu tweets. A future researcher could expand the scope by continuously collecting tweets on a public cloud and applying big data applications, such as Hadoop and MapReduce, to perform predictions using several months of historical data or even years for a larger geographical area.

The Whole Foods Market Trends Council – a collective of more than 50 Whole Foods Market team members ranging from foragers and buyers to culinary experts – develop these trend predictions each year through a combination of deep industry experience, keen observation of consumer preferences, and collaborative sessions with emerging and established brands.

An international group of biologists is calling for data collection on a global scale to improve forecasts of how climate change affects animals and plants.

read more

New industry standard to provide both benefits decision support for employees and medical plan-insight and ROI tools for employers to construct more cost-effective medical benefit offerings

How Entrapeer is reshaping the future of trend prediction and helping businesses stay ahead of the curve.

Nandjui Richard Koutouan, MBA, is a finance and strategy leader in the technology sector at Microsoft.

AI developers DataRobot and Palantir Technologies Inc have entered into a new partnership designed to create unique, agile and real-time solutions to help solve the most pressing demand forecasting problems.

PredictHQ has announced its Demand Impact Pattern for severe weather events, with data sets to help businesses prepare for major weather events and mitigate overall impact by integrating into machine learning models for demand forecasting.

CJ Lang & Son Ltd, the wholesaler for SPAR in Scotland, and the major Scottish convenience store franchise with over 300 stores across the country, has selected RELEX, provider of unified supply chain and retail planning solutions, to automate and optimise its supply chain processes.

Logility, Inc., the prescriptive supply chain planning solutions provider, has signed a definitive agreement to acquire Garvis, a visionary SaaS startup that combines large language models (ChatGPT) with AI-native demand forecasting.

By Rudrendu Kumar Paul and Bidyut Sarkar

Embracing the Future of Supply Chain Management: An Exploration of AI's Transformative Impact on Demand Forecasting and its Potential to Navigate Global Uncertainties.

Location: Electronic Resource- 

Fossil Fuels Expert Roundtable: Forecasting Forum 2018 12 February 2018 — 2:00PM TO 5:30PM Anonymous (not verified) 18 December 2017 Chatham House, London

This forum will present the latest thinking from senior researchers on the dynamics that will affect fossil fuels investment and markets in the year ahead. The first session will assess the various factors keeping oil and gas prices from bouncing back and will consider conditions and political developments that could influence markets in the year ahead. The second session will assess the future of the power sector and what this means for the fossil fuels industry.

Attendance at this event is by invitation only.

Forecasting Forum 2019 29 January 2019 — 2:00PM TO 5:30PM Anonymous (not verified) 17 December 2018 Chatham House | 10 St James's Square | London | SW1Y 4LE

This annual forum, previously held as part of the Fossil Fuels Expert Roundtable but now re-branded under the Energy Transitions Roundtable, presents the latest thinking from the Energy, Environment and Research Department’s senior research team on the dynamics that will affect fossil fuels investment and markets in the year ahead. This year, the forum will have three sessions:

Session 1 | 14:05 - 15:00 | Climate Trends

In December, a ‘playbook’ to implement the 2015 Paris Agreement was agreed by 196 countries at the UN’s COP24 in Poland. Despite this success, challenges surrounding common reporting requirements, degree-pathways to pursue, increasing ambition and the implementation of NDCs still remain. In this session, Pete Betts, former Head of International Climate and Energy at the UK Department for Business, Energy, and Industrial Strategy, will reflect on developments in the climate agenda and what action should be taken both in the UK and internationally against the backdrop of Brexit.

Session 2 | 15:15 - 16:15 | An Outlook for Oil in 2019

The future of crude oil prices for 2019 is perhaps more uncertain than it has been for several years. Following a period between 2014-17 when over-supply banished geopolitics from influencing the oil price, the market appears to be struggling to price political risk. Recently the OPEC Plus agreement was renewed in an effort to curtail production and defend prices but its effectiveness is in question as the shale technology revolution in the US continues to add to global supply - but for how long? Meanwhile, US relations with Saudi Arabia remain uncertain in the aftermath of the murder of Jamal Khashoggi: how might Saudi oil policy unfold? Similarly, how might Iran respond to President Trump’s unilateral abrogation of the JCPOA agreement? In this session, Paul Stevens looks at the geopolitical factors that might influence crude oil prices in 2019.

Session 3 | 16:30 - 17:30 | An Outlook for Coal

The rapid phase-out of coal-fired power stations is crucial to the delivery of the goals of the Paris Agreement and to the safeguarding of clean air and water and public health. Some policy and economic developments show that the coal sector is in structural decline, and there is growing international momentum behind coal phase-out. At the same time, many of the largest coal trading countries and companies continue to argue the short-term profitability of the sector but at what cost? This session will explore the national and international risks that continued investment in coal present and the developments that could change this in the year ahead.

Attendance at this event is by invitation only.

Forecasting Forum 2020 17 February 2020 — 2:00PM TO 5:00PM Anonymous (not verified) 15 January 2020 Chatham House | 10 St James's Square | London | SW1Y 4LE

The Forecasting Forum 2020 will present the latest thinking from the Chatham House Energy, Environment and Resources Department’s senior research team on the dynamics that will affect fossil fuel and energy investments and markets in the year ahead.

14:00 - 14:30 | Introduction and Climate Risks Outlook

In the last decade, following the financial crisis, the literature on systemic risks has grown. Systemic risks occur when complex, non-linear, interconnected systems fail, often through relatively small perturbations, as their impacts cascade and amplify across the system. Within this context, climate change is a ‘threat multiplier’ with the risks increasing in scale, frequency and magnitude. Just as complex systems can pass thresholds and tip from a functional state to a non-functional state, so can societies and people’s attitudes. Together risk cascades or systemic risks and attitudinal tipping points have the potential to rapidly change the way the world works.

Professor Tim Benton will open the Forecasting Forum 2020 with reflections on what this might mean for the pace and linearity of the fossil fuel transition.

14:30 - 15:30 | Session 1: An Outlook on Oil Prices in 2020

In this session, Professor Paul Stevens will argue that the recent events associated with the assassination of Iranian General Qasem Soleimani have exacerbated the sensitivity of oil markets to political events and brought ‘geopolitics’ back into global oil prices. Up to 2014, geopolitics played a key role in determining oil prices in the paper markets where perceptions and expectations ruled. By 2014, the world was so oversupplied with real oil barrels that the oil price collapsed and little attention was given to geopolitical events as geopolitics became marginalized in the determination of crude oil prices. However, recent events in the Middle East suggest that prices will become increasingly volatile but, at the same time, benefit from a rising geopolitical premium.

15:45 - 16:45 | Session 2: An Outlook for Energy in 2020

Recent years have brought significant disruption to the European power sector. Not only are many of Europe’s major utilities restructuring their businesses in light of decarbonization and technological developments but Brexit has distracted - and detracted from - efforts to create more systemic energy linkages between the UK and the rest of Europe. During his presentation, Antony Froggatt will draw on his ongoing research to outline what he believes are the prevailing challenges and opportunities for the European power sector over the coming year while highlighting some of the most significant global trends.

Please note, attendance at this event is by invitation only.

Forecasting forum 2021 28 January 2021 — 12:30PM TO 2:00PM Anonymous (not verified) 21 January 2021 Online

Speakers explore the dynamics that will likely affect fossil fuel demand, energy investments and markets in the year ahead.

The Forecasting Forum 2021 presents the latest thinking from the Energy, Environment and Resources Programme’s senior research team and colleagues on the dynamics that will likely affect fossil fuel demand, energy investments and markets in the year ahead.

Focus is given to the impacts of the COVID-19 pandemic, the first 100 days of the new Biden administration in the US, and the run-up to COP26. The extraordinary developments over the last year have demonstrated the need consider and discuss a wide range of possible futures and the factors that affect them to help improve system resilience and increase stability, whilst achieving sustainability.

For the first time, this annual event was run online and consisted of a panel discussion on what the year ahead might hold.

Forecasting forum 2022 2 February 2022 — 2:00PM TO 3:30PM Anonymous (not verified) 17 January 2022 Online

The Environment and Society Programme’s senior research team will discuss the emerging geopolitical trends that may impact energy markets and investments in 2022.

The Forecasting Forum 2022 presents the latest thinking from the Environment and Society Programme’s senior research team on the dynamics that will likely affect fossil fuel demand, energy investments and markets in the year ahead.

The event will discuss a wide range of emerging geopolitical trends that may impact energy markets and investments in 2022, including continuing uncertainty around COVID-19, fuel price changes, US political direction and progress of President Biden’s climate agenda, and growing shareholder activism within some of the largest energy companies. Moreover, the implications of pledges made at COP26 will start to materialize, ahead of a new climate scenarios report by the UN’s Intergovernmental Panel on Climate Change and the COP27 summit in Egypt. In this respect, the panel will assess whether 2022 could prove to be a decisive year for the energy transition. 

I am gratified to see the continuing adoption of Forecast Value Added by organizations worldwide. FVA is an easy to understand and easy to apply approach for identifying bad practices in your forecasting process. And I'm particularly gratified to see coverage of FVA in two new books, which the authors [...]

The post Vandeput's Data Science for Supply Chain Forecasting (book excerpt) appeared first on The Business Forecasting Deal.

What makes something easy (or difficult) to forecast? This question was answered by Prof. Rob Hyndman on the Forecasting Impact podcast (February 6, 2021), and it's worth a look at his response. Rob was recently named a Fellow of the International Institute of Forecasters, and is someone who is known [...]

The post Hyndman's 5 Conditions for Easy Forecasting appeared first on The Business Forecasting Deal.

M6 Financial Forecasting Competition The Makridakis Open Forecasting Center has announced the M6 Financial Forecasting Competition, to begin in February 2022. This will be a "live" competition running through February 2023, with a focus on forecasts of stock price (returns) and risk, and on investment decisions based on the forecasts. [...]

The post M6 Financial Forecasting Competition announced appeared first on The Business Forecasting Deal.

I've never been much of a fan of forecasting approaches to intermittent demand. In situations like intermittent demand (or other areas where we have little hope of reasonably accurate forecasts), my thinking is "why bother?" If we can't expect to solve the problem with forecasting, we need a different approach. [...]

The post Intermittent Demand Forecasting (new book by Boylan and Syntetos) appeared first on The Business Forecasting Deal.

We’re expanding flood forecasting to over 100 countries and making our breakthrough AI model available to researchers and partners.

$60 million will be spent on a new supercomputer to improve the accuracy of one of the world's most vital weather forecasts

With improvements, the ‘Mausam Mission’ will transform how weather information can help India become climate smart

IMD has temporarily closed down the observatory, which started functioning in 1931, in the wake of an eviction notice issued by Port department

In an interaction with ETCIO, Krishnan Venkateswaran, Chief Digital & Information Officer, Titan, explains how augmented intelligence and machine learning are being leveraged for innovating design & creativity in the company.

Team of scientists and engineers head to the heart of earthquake country to learn more about predicting when and where an earthquake will happen — before the

InsurTech Futures: The firm is looking to partner with commercial and HNW brokers.

Shareholders will be ecstatic, with their stake up 30% over the past week following ObsEva SA's (NASDAQ:OBSV) latest...

With time-series decomposition, we were able to infer that the consumers were waiting for the highest sale of the year rather than buying up-front.

Paul Saffo, technology forecaster and author of the HBR article "Six Rules for Effective Forecasting."

Paradoxically and fatally, just when risk of a downturn is at its highest, optimism also ends up peaking! So be careful with your forecasts; and even more careful with the forecasts of others.

Kostya Medvedovsky writes: I wanted to direct your attention to the University of Texas COVID-19 Modeling Consortium’s new projections. They’re very similar to the IMHE model you’ve covered before, and had some calibration issues. However, per the writeup by Spencer Woody et al., they do three things you may be interested in: They fix an […]

Over the last several decades, the overall air quality goal in the United States has been to protect public health and clear skies by reducing emissions. At the same time, however, the risk of catastrophic fire has been rising in forests around the country as overly dense trees and understory brush crowd the stands.

Fashion trend forecasting is a crucial task for both academia and industry. Although some efforts have been devoted to tackling this challenging task, they only studied limited fashion elements with highly seasonal or simple patterns, which could hardly reveal the real fashion trends. Towards insightful fashion trend forecasting, this work focuses on investigating fine-grained fashion element trends for specific user groups. We first contribute a large-scale fashion trend dataset (FIT) collected from Instagram with extracted time series fashion element records and user information. Further-more, to effectively model the time series data of fashion elements with rather complex patterns, we propose a Knowledge EnhancedRecurrent Network model (KERN) which takes advantage of the capability of deep recurrent neural networks in modeling time-series data. Moreover, it leverages internal and external knowledge in fashion domain that affects the time-series patterns of fashion element trends. Such incorporation of domain knowledge further enhances the deep learning model in capturing the patterns of specific fashion elements and predicting the future trends. Extensive experiments demonstrate that the proposed KERN model can effectively capture the complicated patterns of objective fashion elements, therefore making preferable fashion trend forecast.