Rajesh Jain

HBR: “Optimal machine learning, overcomes the significant shortcomings in existing supply-chain-planning methods. It has three key components: a decision-support engine, a digital twin, and an end-to-end data architecture.” On digital twin: “A key requirement for the OML decision-support engine to work is a detailed digital representation of the entire supply-chain network, all material flows, and the decision-making processes of all involved parties. By modeling the performance of the supply chain in a highly detailed manner at the granular level of each transaction, the digital twin allows supply chain planners to quantify accurate KPIs for both past and future demand-and-supply scenarios. Such a digital representation has two advantages. First, its calculations of the impact of historical decisions can be compared with the actual results computed by existing business systems, which validates its ability to measure performance accurately and thereby gives management confidence in the system. Second, it can be used to test the effects of alternative supply-chain scenarios or strategies on KPIs. For example, what if the shipment lead times double because of slowdowns in a specific shipping lane? Or how would the disruption of a distribution center affect revenue? Or what would be the best way to reroute shipments to stores served by that distribution center? Together, these two capabilities—historical analysis and predictive power—make it possible for managers to accurately evaluate risk-mitigation strategies, such as alternative sources of supply and transportation, alternative stocking locations, revised production schedules, and the use of product substitutes. As a result, managers can make better decisions.”

James Ball: “I spent weeks asking where, if anywhere, news is discussed and shared on sober terms online. A few diehards of the early internet tried to suggest the resurgence of RSS feeds—automated notifications of new articles on a particular topic on a particular site. They were barely even convincing themselves. The most surprising answer I found—given that it was once considered the villain of the piece—was Reddit. For those who haven’t used it, Reddit is a bulletin-board style social network split into quasi-autonomous “subreddits” focused on different topics. Each of these is managed by volunteer moderators and administrators, who can set and enforce rules of conduct within that community. These subreddits are much smaller than Twitter. The largest—r/worldnews, to use Reddit’s naming format for these threads—comprises around thirty-five million users, of whom around twenty thousand to forty thousand are online at any one time.”

NYTimes: “Economists typically measure productivity as a simple ratio: the total amount of output an economy produces per hour worked by its labor force. On that score, productivity increased 2.7 percent in 2023, according to the Bureau of Labor Statistics, and over the last two quarters has been growing at more than double the rate from 2005 to 2019. On a less technical level, productivity can generally be explained by the old axiom about “doing more with less,” or the folksy virtue of “getting the biggest bang for your buck.” Economists tend to sigh with relief whenever they see a gain in productivity, because it offers a potential win-win for workers, customers and business owners: If businesses can make as much money or more in fewer work hours, then — according to standard economic logic — they can make more per hour, reinvest in operations and pay workers a bit more without sacrificing profitability (or leaning on price increases to push profits higher). As Joseph Brusuelas and Tuan Nguyen, economists at the consulting firm RSM, put it in a note in late January: “The increase in American productivity over the past year, if sustained, is a potential game changer for the economy that represents that mythical rising tide that lifts the living standards of all.””

Economist: “Costco is the world’s third-biggest retailer, behind Walmart and Amazon. Though its sales are less than half of Walmart’s, its return on capital, at nearly 20%, is more than twice as high…Costco stores stock a limited selection of about 3,800 distinct items. Sam’s Club, Walmart’s Costco-like competitor, carries about 7,000. A Walmart superstore has around 120,000. Buying more from fewer suppliers gives the company even greater bargaining heft, lowering prices further. By limiting its range, Costco can better focus on maintaining quality. Less variety in stores helps it use space more efficiently: its sales per square foot are three times that of Walmart. And with fewer products, Costco turns over its wares almost twice as fast as usual for retailers, meaning less capital gets tied up in inventory. It has also expanded its own brand, Kirkland Signature, which now accounts for over a quarter of its sales, well above average for a retailer. Its margins on its own-brand products are about six percentage points higher than for brands such as Hershey or Kellogg’s.”

WSJ: “Generative AI is less suited to quickly building mass audiences—it doesn’t create a platform of users. But it is ideally suited for transforming large organizations by making people and processes radically more productive. “When the social mobile cloud started in 2007, mobile was a big distribution advantage, you could go out and acquire customers, letting them take advantage of the global supply chain and build these full stack companies. AI doesn’t give me any of that. It really is a transformation advantage,” [Hemant] Taneja said. He added, “The bulk of the value is to me about what is the role of AI in transforming both from a vertical standpoint and from a business function standpoint. And most of our energy is looking at how are we going to do that? What is the role of AI in industries like healthcare? What is the role of AI in functions like marketing and customer support?””

Economist: “Turkey is now the third-biggest exporter of scripted series in the world—behind only America and Britain. Between 2020 and 2023 global demand for Turkish shows grew by 184%, compared with 73% for Korean dramas, according to Parrot Analytics, a data firm. Turkish shows are popular not just in the Middle East but also in Europe and Latin America. Last year the three biggest importers of new Turkish shows were Spain, Saudi Arabia and Egypt. The Istanbul Chamber of Commerce estimates that Turkey’s television exports earned $600m in 2022; some analysts predict their sales will soon total billions.”

McKinsey: “Imagine a world where marketers have no creative constraints. A world where they can make the right offer at the right time for the right person—in a communication that feels like a cohesive whole, rather than like some disjointed Mad Libs concoction. A world where efficiency gains from automation and automated-content generation go hand in hand with increased customer insights. A world where customers save time and effort finding and accessing the goods and services they want and need. A world where marketers can better meet and deliver customer value and focus on innovation. Generative AI (gen AI) brings this holy grail of hyperpersonalization at scale close to reality. Gen AI is making it possible to revolutionize consumer marketing as we currently know it. At an individual-company level, marketing campaigns that once required months of content design, insight generation, and customer targeting can be rolled out in weeks or even days, often with at-scale personalization and automated testing. Website development and customer service tasks are too often the bottlenecks in interactions with individual consumers. But when executed well, they can induce greater engagement and improve satisfaction. Marketers can simultaneously analyze and interpret text, image, and video data to better understand innovation opportunities. Gen AI is powering granular personalization in ways that just weren’t possible before.”

WSJ: “For decades, seeking knowledge online has meant googling it and clicking on the links the search engine offered up. Search has so dominated our information-seeking behaviors that few of us ever think to question it anymore. But AI is changing all of that, and fast. A new generation of AI-powered “answer engines” could make finding information easier, by simply giving us the answers to our questions rather than forcing us to wade through pages of links. Meanwhile, the web is filling up with AI-generated content of dubious quality. It’s polluting search results, and making traditional search less useful. The implications of this shift could be big. Seeking information using a search engine could be almost completely replaced by this new generation of large language model-powered systems, says Ethan Mollick, an associate professor at the Wharton School of the University of Pennsylvania who has lately made a name for himself as an analyst of these AIs. This could be good for consumers, but it could also completely upend the delicate balance of publishers, tech giants and advertisers on which the internet as we know it has long depended.”

Andy Mukherjee: “online education is still a viable proposition in the world’s most-populous nation, though it’s the test-prep market that has real demand, not K-12 or coding. India has a little over 100,000 medical and dentistry placements, with more than 1.5 million jostling to get in. The 23 Indian Institutes of Technology accept only 17,000, after a main test followed by an advanced exam…Physics Wallah now offers courses for 35 Indian exam categories, including civil services and army recruitment. Cofounder Maheshwari is opening one new offline center every five days. Annual sales have more than doubled in one year to 20 billion rupees ($240 million), supported by around $50 million from assorted acquisitions. About 54% of the remaining $190 million is from online tutoring, while another 43% comes from 50-plus physical locations, where more than 180,000 students shell out $500 apiece. A money-making core generates resources for expansion. The buzzwords are affordability and profitability.”

Bloomberg on the need to declutter (like Marie Kondo): “The spring cleaning idea has two benefits over top-down management. First, it takes place every year and thereby becomes part of the company’s way of doing things. You are preparing for the next annual ritual and looking out for things to cut. Second, it hands power to the managed rather than the managers. It is the managed who bear the brunt of the “tragedy of the commons,” and the managed who usually have the best ideas for what needs to be preserved and what needs to be changed. Top- down initiatives such as slashing meetings usually go too far at first (some meetings are necessary) and then fade as the old habits reassert themselves and the old managers rebuild their empires. A regular spring cleaning will keep a constant pressure on management to preserve what matters and junk what gets in the way of people doing their jobs.”

Evan Carlisle: “Misinformation gets washed away when people have open dialogues and critical discussions with those who read different sources and hold different opinions. The core issue is that people aren’t engaging in the conversations that are necessary to dispel misinformation. The increasing atomization of society—caused by political polarization, isolating lifestyles and the growth of ever more specific subcultures—makes it harder for people to go out into the world and talk to one another. Instead, they get trapped on social media by echo chambers that keep people from interacting directly with one another. These problems are influencing swaths of society, not because of any single social-media app but because of continuing social trends. Governments cannot regulate this away. At best, all they can do is remind people to step outside and talk to each other.”

Arnold Kling (writing after he was mugged): “For public safety, I don’t see a libertarian alternative to having households and business get together and pool resources. Ultimately, the provider of protection services needs to be able to use force. And that ability to use force gives it the potential to turn on its clients. Let’s drop the libertarian pretense, and call the force that provides safety for its constituents a government. The relationship between constituents and government is bound to get complicated. They are playing a repeated game with one another. Incentives are difficult to align. There is a trade-off between the government being too authoritarian and too lax. The challenges posed by political theory cannot be boiled down to a simple catch-phrase or a permanent solution.”

Bluecore: “For a growth marketing strategy to succeed, it must be developed through the lens of the customer. Strategy needs to start with groups of customers — first-time buyers, lapsed buyers, and varieties of repeat buyers, sorted by the time frame in which they were acquired. It needs to distinguish VIPs from a promising tier just below and the vast movable middle underneath. A strategy that prioritizes customers over channels enables brands to develop hypotheses, launch experiments, and test and learn their way to success. A customer-driven strategy encourages brands to put less emphasis on metrics that describe the outcomes of a particular channel and to put more focus on metrics that describe the behavior of customers and in particular, customer spend over time: retention and reactivation, purchase frequency, average order value, and customer lifetime value. With a customer-driven strategy, marketers no longer obsess over channel tactics in isolation; instead, they look to encourage specific behaviors by specific segments or cohorts of customers with relevant channel tactics. Channels become secondary to, and enablers of, corporate value creation. Today’s combination of unusual market conditions and internal dysfunction gives marketing leaders a chance to reset expectations, and to use a new approach to promote customer-led growth to drive short-term gains and long-term profit. That approach is customer movement.”

NYTimes: “There have been just a handful of moments over the centuries when we have experienced a huge shift in the skills our economy values most. We are entering one such moment now. Technical and data skills that have been highly sought after for decades appear to be among the most exposed to advances in artificial intelligence. But other skills, particularly the people skills that we have long undervalued as “soft,” will very likely remain the most durable. That is a hopeful sign that A.I. could usher in a world of work that is anchored more, not less, around human ability. A moment like this compels us to think differently about how we are training our workers, especially the heavy premium we have placed on skills like coding and data analysis that continue to reshape the fields of higher education and worker training. The early signals of what A.I. can do should compel us to think differently about ourselves as a species. Our abilities to effectively communicate, develop empathy and think critically have allowed humans to collaborate, innovate and adapt for millenniums. Those skills are ones we all possess and can improve, yet they have never been properly valued in our economy or prioritized in our education and training. That needs to change.”

FT: “Google, Meta, ByteDance, Alibaba and Amazon are now the five biggest global sellers of advertising. Together they have grown advertising revenue 25.4 per cent on a compound annual basis from 2016 to 2022, against a 9.3 per cent rise in the broader market. In 2023, almost 70 per cent of the $889bn in revenues in the advertising industry was classed as digital by GroupM, the world’s largest media buying agency. By 2028, it expects digital advertising on social media platforms such as TikTok or YouTube to make up more than three-quarters of the market — larger than the entire advertising industry in 2022.”

Economist: “Recent advances in AI—most notably large language models (LLMs)—allow leaders, for the first time, to glean nuanced insights into their corporate culture from how employees talk about their company in their own words. Rather than answering reams of questions on a five-point scale, workers can now simply explain what is and isn’t working in their organisation and offer suggestions for how it can improve. The AI can do the heavy lifting, providing much more granular classification of comments and assessment of sentiment. Freed from the shackles of traditional surveys, organisations can use AI to gather and process employee feedback from many sources. The volume of available feedback is staggering. Combining free text from internal surveys, performance feedback provided to managers, online employer reviews and other sources equates to tens of thousands of pages of data each year for a large company. Until recently, organisations had to rely on crude tools such as word clouds or search keywords to gain insights from this trove of information.”

Fortune: “Instead of pitching AI as a tool for businesses to accomplish arcane internal tasks, Sierra is betting on easy-to-understand, pragmatic uses of AI technology like conversational “agents” who can interact with customers for support, account management and other issues. These AI agents can answer questions faster than humans and at much lower cost, the company says…In a departure from the conventional Silicon Valley playbook, Sierra is actually building the AI agents for customers, rather than just selling the tools for customers to do it themselves. It’s a business model that may not scale as rapidly, but the idea is that many companies, even very large ones, don’t have the in-house resources, expertise, or desire to take on this kind of complex project…A typical agent based on Sierra’s technology uses four or five different AI models when it receives a message from a user – one of the models might generate a response, for example, while another model might be tapped to prevent hallucinations. Sierra uses a mix of proprietary and open source large language models, including frontier models from OpenAI and Microsoft that are tweaked by their team of researchers to fit a customer’s use case.”

Akash Prakash: “In India, while such a company may initially receive a lower valuation, it becomes a unique focal point, attracting immense investor attention and analyst interest. The company can shape the narrative on growth and valuation metrics. If your company is seen as one of the leaders in an industry where India is structurally advantaged, valuations can expand. Just see the valuation given to Indian IT, generic pharma and auto component stocks. They are off the charts and many multiple points higher than global peers, and been so for years. Today, there is hope of this being the SaaS moment for India and these companies being the IT services of 20 years ago. I would argue that SaaS companies listed in India will trade up eventually to a premium over global peers. There may be initial valuation arbitrage to list overseas if the company is unprofitable, but this valuation gap will close as profitability is established.”

NYTimes: “BYD’s sales, over 80 percent of them in China, have grown by about a million cars in each of the past two years. The last automaker to accomplish that in even one year in the American market was General Motors — and that was in 1946, after G.M. had suspended passenger car sales during the four preceding years because of World War II. “BYD’s growth is unlike anything the industry has seen in many decades,” said Matt Anderson, curator of transportation at the Henry Ford Museum in Dearborn, Mich. Based in Shenzhen, the hub of China’s electronics industry, BYD has shown how Chinese carmakers can tap the country’s dominance of electrical products. No company has benefited as much from China’s embrace of battery-electric cars and plug-in gasoline-electric cars. These vehicles together make up 40 percent of China’s car market, the world’s largest, and are expected to be more than half next year.”

Rahm Emanuel: “Before I arrived in Tokyo as ambassador two years ago, a number of foreign policy experts cautioned me that Japan moves slowly. They urged me to find a virtue in patience when dealing with the government — which I knew would be tricky for someone like me who has zero patience. I needn’t have worried. Two years later, one thing is clear: The experts didn’t know much about the new Japan. No one predicted that this would be an era of Japanese transformation, a time when the Japanese surprised nearly everyone with what they can and will do.”

McKinsey: “For decades we’ve seen companies’ fortunes rise and fall based on their ability to react to, and recover quickly from, geopolitical shocks, technological advances, economic uncertainty, competitors’ bold moves, and other disruptions. Amid this volatility, which these days is accelerating rather than abating, many have a hard time staying the course. But some continue to survive and thrive despite the challenges. Why do these companies manage to succeed, year after year—operationally, financially, and otherwise—while others don’t? Twenty-plus years of proprietary McKinsey research tells us that one of the main reasons is organizational health. Organizational health refers to how effectively leaders “run the place”—that is, how they make decisions, allocate resources, operate day to day, and lead their teams with the goal of delivering high performance, both near term and over time. Organizational health comprises three elements: how well the entire organization rallies around a common vision and strategy, how well the organization executes its strategy, and how well the organization innovates and renews itself over time.”